vlad/reverse-skills-max
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

reverse-skills-max: initial public release (restored, redacted, hardened)

Browse Source
This commit is contained in:
baradok609hecl1pq6qi
2026-10-20 02:17:15 +03:00
commit da24c2bd20
2227 changed files with 443931 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

201
vendor-new/Anthropic-Cybersecurity-Skills/skills/analyzing-pdf-malware-with-pdfid/LICENSE Normal file
View File

@@ -0,0 +1,201 @@
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
1. Definitions.
"License" shall mean the terms and conditions for use, reproduction,
and distribution as defined by Sections 1 through 9 of this document.
"Licensor" shall mean the copyright owner or entity authorized by
the copyright owner that is granting the License.
"Legal Entity" shall mean the union of the acting entity and all
other entities that control, are controlled by, or are under common
control with that entity. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity
exercising permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation
source, and configuration files.
"Object" form shall mean any form resulting from mechanical
transformation or translation of a Source form, including but
not limited to compiled object code, generated documentation,
and conversions to other media types.
"Work" shall mean the work of authorship, whether in Source or
Object form, made available under the License, as indicated by a
copyright notice that is included in or attached to the work
(an example is provided in the Appendix below).
"Derivative Works" shall mean any work, whether in Source or Object
form, that is based on (or derived from) the Work and for which the
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to the Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity
on behalf of whom a Contribution has been received by the Licensor and
subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the
Work or Derivative Works thereof in any medium, with or without
modifications, and in Source or Object form, provided that You
meet the following conditions:
(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and
(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and
(c) You must retain, in the Source form of any Derivative Works
that You distribute, all copyright, patent, trademark, and
attribution notices from the Source form of the Work,
excluding those notices that do not pertain to any part of
the Derivative Works; and
(d) If the Work includes a "NOTICE" text file as part of its
distribution, then any Derivative Works that You distribute must
include a readable copy of the attribution notices contained
within such NOTICE file, excluding any notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.
You may add Your own copyright statement to Your modifications and
may provide additional or different license terms and conditions
for use, reproduction, or distribution of Your modifications, or
for any such Derivative Works as a whole, provided Your use,
reproduction, and distribution of the Work otherwise complies with
the conditions stated in this License.
5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade
names, trademarks, service marks, or product names of the Licensor,
except as required for reasonable and customary use in describing the
origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or
agreed to in writing, Licensor provides the Work (and each
Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Work and assume any
risks associated with Your exercise of permissions under this License.
8. Limitation of Liability. In no event and under no legal theory,
whether in tort (including negligence), contract, or otherwise,
unless required by applicable law (such as deliberate and grossly
negligent acts) or agreed to in writing, shall any Contributor be
liable to You for damages, including any direct, indirect, special,
incidental, or consequential damages of any character arising as a
result of this License or out of the use or inability to use the
Work (including but not limited to damages for loss of goodwill,
work stoppage, computer failure or malfunction, or any and all
other commercial damages or losses), even if such Contributor
has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing
the Work or Derivative Works thereof, You may choose to offer,
and charge a fee for, acceptance of support, warranty, indemnity,
or other liability obligations and/or rights consistent with this
License. However, in accepting such obligations, You may act only
on Your own behalf and on Your sole responsibility, not on behalf
of any other Contributor, and only if You agree to indemnify,
defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason
of your accepting any such warranty or additional liability.
END OF TERMS AND CONDITIONS
APPENDIX: How to apply the Apache License to your work.
To apply the Apache License to your work, attach the following
boilerplate notice, with the fields enclosed by brackets "[]"
replaced with your own identifying information. (Don't include
the brackets!) The text should be enclosed in the appropriate
comment syntax for the file format. Please do not remove or change
the license header comment from a contributed file except when
necessary.
Copyright 2026 mukul975
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.

357
vendor-new/Anthropic-Cybersecurity-Skills/skills/analyzing-pdf-malware-with-pdfid/SKILL.md Normal file
View File

@@ -0,0 +1,357 @@
---
name: analyzing-pdf-malware-with-pdfid
description: 'Analyzes malicious PDF files using PDFiD, pdf-parser, and peepdf to
identify embedded JavaScript, shellcode, exploits, and suspicious objects without
opening the document. Determines the attack vector and extracts embedded payloads
for further analysis. Activates for requests involving PDF malware analysis, malicious
document analysis, PDF exploit investigation, or suspicious attachment triage.
'
domain: cybersecurity
subdomain: malware-analysis
tags:
- malware
- PDF-analysis
- document-malware
- PDFiD
- static-analysis
version: 1.0.0
author: mahipal
license: Apache-2.0
nist_csf:
- DE.AE-02
- RS.AN-03
- ID.RA-01
- DE.CM-01
mitre_attack:
- T1204.002
- T1566.001
- T1059.007
- T1027
---
# Analyzing PDF Malware with PDFiD
## When to Use
- A suspicious PDF attachment has been flagged by email security or reported by a user
- You need to determine if a PDF contains embedded JavaScript, shellcode, or exploit code
- Triaging PDF documents before opening them in a sandbox or analysis environment
- Extracting embedded executables, scripts, or URLs from malicious PDF objects
- Analyzing PDF exploit kits targeting Adobe Reader or other PDF viewer vulnerabilities
**Do not use** for analyzing the rendered visual content of a PDF; this is for structural analysis of the PDF file format for malicious objects.
## Prerequisites
- Python 3.8+ with Didier Stevens' PDF tools installed (`pip install pdfid pdf-parser`)
- peepdf installed for interactive PDF analysis (`pip install peepdf`)
- pdftotext from poppler-utils for extracting text content safely
- YARA with PDF-specific rules for malware family identification
- Isolated analysis VM without a PDF reader installed (prevent accidental opening)
- CyberChef for decoding embedded Base64, hex, or deflate streams
## Workflow
### Step 1: Initial Triage with PDFiD
Scan the PDF for suspicious keywords and structures:
```bash
# Run PDFiD to identify suspicious elements
pdfid suspect.pdf
# Expected output analysis:
# /JS - JavaScript (HIGH risk)
# /JavaScript - JavaScript object (HIGH risk)
# /AA - Auto-Action triggered on open (HIGH risk)
# /OpenAction - Action on document open (HIGH risk)
# /Launch - Launch external application (HIGH risk)
# /EmbeddedFile - Embedded file (MEDIUM risk)
# /RichMedia - Flash content (MEDIUM risk)
# /ObjStm - Object stream (used for obfuscation)
# /URI - URL reference (contextual risk)
# /AcroForm - Interactive form (MEDIUM risk)
# Run with extra detail
pdfid -e suspect.pdf
# Run with disarming (rename suspicious keywords)
pdfid -d suspect.pdf
```
```
PDFiD Risk Assessment:
━━━━━━━━━━━━━━━━━━━━━
HIGH RISK indicators (any count > 0):
/JS, /JavaScript -> Embedded JavaScript code
/AA -> Automatic Action (triggers without user interaction)
/OpenAction -> Code runs when document is opened
/Launch -> Can launch external executables
/JBIG2Decode -> Associated with CVE-2009-0658 exploit
MEDIUM RISK indicators:
/EmbeddedFile -> Contains embedded files (could be EXE/DLL)
/RichMedia -> Flash/multimedia (Flash exploits)
/AcroForm -> Form with possible submit action
/XFA -> XML Forms Architecture (complex attack surface)
LOW RISK indicators:
/ObjStm -> Object streams (obfuscation technique)
/URI -> External URL references
/Page -> Number of pages (context only)
```
### Step 2: Parse PDF Structure with pdf-parser
Examine suspicious objects identified by PDFiD:
```bash
# List all objects referencing JavaScript
pdf-parser --search "/JavaScript" suspect.pdf
pdf-parser --search "/JS" suspect.pdf
# List all objects with OpenAction
pdf-parser --search "/OpenAction" suspect.pdf
# Extract a specific object by ID (example: object 5)
pdf-parser --object 5 suspect.pdf
# Extract and decompress stream content
pdf-parser --object 5 --filter --raw suspect.pdf
# Search for embedded files
pdf-parser --search "/EmbeddedFile" suspect.pdf
# List all objects with their types
pdf-parser --stats suspect.pdf
```
### Step 3: Extract and Analyze Embedded JavaScript
Pull out JavaScript code from PDF objects:
```bash
# Extract JavaScript using pdf-parser
pdf-parser --search "/JS" --raw --filter suspect.pdf > extracted_js.txt
# Alternative: Use peepdf for interactive JavaScript extraction
peepdf -f -i suspect.pdf << 'EOF'
js_analyse
EOF
# peepdf interactive commands for JS analysis:
# js_analyse - Extract and show all JavaScript code
# js_beautify - Format extracted JavaScript
# js_eval <object> - Evaluate JavaScript in sandboxed environment
# object <id> - Display object content
# rawobject <id> - Display raw object bytes
# stream <id> - Display decompressed stream
# offsets - Show object offsets in file
```
```python
# Python script for comprehensive PDF JavaScript extraction
import subprocess
import re
# Extract all streams and search for JavaScript
result = subprocess.run(
["pdf-parser", "--stats", "suspect.pdf"],
capture_output=True, text=True
)
# Find object IDs containing JavaScript references
js_objects = []
for line in result.stdout.split('\n'):
if '/JavaScript' in line or '/JS' in line:
obj_id = re.search(r'obj (\d+)', line)
if obj_id:
js_objects.append(obj_id.group(1))
# Extract each JavaScript-containing object
for obj_id in js_objects:
result = subprocess.run(
["pdf-parser", "--object", obj_id, "--filter", "--raw", "suspect.pdf"],
capture_output=True, text=True
)
print(f"\n=== Object {obj_id} ===")
print(result.stdout[:2000])
```
### Step 4: Analyze Embedded Shellcode
Extract and examine shellcode from PDF exploits:
```bash
# Extract raw stream data for shellcode analysis
pdf-parser --object 7 --filter --raw --dump shellcode.bin suspect.pdf
# Analyze shellcode with scdbg (shellcode debugger)
scdbg /f shellcode.bin
# Alternative: Use speakeasy for shellcode emulation
python3 -c "
import speakeasy
se = speakeasy.Speakeasy()
sc_addr = se.load_shellcode('shellcode.bin', arch='x86')
se.run_shellcode(sc_addr, count=1000)
# Review API calls made by shellcode
for event in se.get_report()['api_calls']:
print(f\"{event['api']}: {event['args']}\")
"
# Use CyberChef to decode hex/base64 encoded shellcode
# Input: Extracted stream data
# Recipe: From Hex -> Disassemble x86
```
### Step 5: Extract Embedded Files and URLs
Pull out embedded executables and linked resources:
```python
# Extract embedded files from PDF
import subprocess
import hashlib
# Find embedded file objects
result = subprocess.run(
["pdf-parser", "--search", "/EmbeddedFile", "--raw", "--filter", "suspect.pdf"],
capture_output=True
)
# Extract embedded PE files by searching for MZ header
with open("suspect.pdf", "rb") as f:
data = f.read()
# Search for embedded PE files
offset = 0
while True:
pos = data.find(b'MZ', offset)
if pos == -1:
break
# Verify PE signature
if pos + 0x3C < len(data):
pe_offset = int.from_bytes(data[pos+0x3C:pos+0x40], 'little')
if pos + pe_offset + 2 < len(data) and data[pos+pe_offset:pos+pe_offset+2] == b'PE':
print(f"Embedded PE found at offset 0x{pos:X}")
# Extract (estimate size or use PE header)
embedded = data[pos:pos+100000] # Initial extraction
sha256 = hashlib.sha256(embedded).hexdigest()
with open(f"embedded_{pos:X}.exe", "wb") as out:
out.write(embedded)
print(f" SHA-256: {sha256}")
offset = pos + 1
# Extract URLs from PDF
result = subprocess.run(
["pdf-parser", "--search", "/URI", "--raw", "suspect.pdf"],
capture_output=True, text=True
)
urls = re.findall(r'(https?://[^\s<>"]+)', result.stdout)
for url in set(urls):
print(f"URL: {url}")
```
### Step 6: Generate Analysis Report
Document all findings from the PDF analysis:
```
Analysis should cover:
- PDFiD triage results (suspicious keyword counts)
- PDF structure anomalies (object streams, cross-reference issues)
- Extracted JavaScript code (deobfuscated if needed)
- Shellcode analysis results (API calls, network indicators)
- Embedded files extracted with hashes
- URLs and external references
- CVE identification if a known exploit is detected
- YARA rule matches against known PDF malware families
```
## Key Concepts
| Term | Definition |
|------|------------|
| **PDF Object** | Basic building block of a PDF file; objects can contain streams (compressed data), dictionaries, arrays, and references to other objects |
| **OpenAction** | PDF dictionary entry specifying an action to execute when the document is opened; commonly used to trigger JavaScript exploits |
| **PDF Stream** | Compressed data within a PDF object that can contain JavaScript, images, embedded files, or shellcode; typically FlateDecode compressed |
| **FlateDecode** | Zlib/deflate compression filter applied to PDF streams; must be decompressed to analyze contents |
| **ObjStm (Object Stream)** | PDF feature storing multiple objects within a single compressed stream; used by malware to hide suspicious objects from simple parsers |
| **JBIG2** | Image compression standard in PDFs; historical source of exploits (CVE-2009-0658, CVE-2021-30860 FORCEDENTRY) |
| **PDF JavaScript API** | Adobe-specific JavaScript extensions available in PDF documents for form manipulation, network access, and OS interaction |
## Tools & Systems
- **PDFiD**: Didier Stevens' tool for scanning PDF documents for suspicious keywords and structures without parsing the full document
- **pdf-parser**: Companion tool to PDFiD for detailed PDF object extraction, stream decompression, and content analysis
- **peepdf**: Python-based PDF analysis tool providing interactive shell for object inspection and JavaScript extraction
- **QPDF**: PDF transformation tool for linearizing, decrypting, and restructuring PDFs for easier analysis
- **scdbg**: Shellcode analysis tool that emulates x86 shellcode execution and logs API calls
## Common Scenarios
### Scenario: Triaging a Phishing PDF with Embedded JavaScript
**Context**: Email gateway flagged a PDF attachment with suspicious JavaScript indicators. The security team needs to determine if it contains an exploit or a social engineering redirect.
**Approach**:
1. Run PDFiD to confirm /JS, /JavaScript, and /OpenAction presence and counts
2. Use pdf-parser to extract the OpenAction object and follow its reference chain
3. Extract the JavaScript code from the referenced stream object (apply FlateDecode filter)
4. Deobfuscate the JavaScript (decode hex strings, resolve eval chains)
5. Determine if the script exploits a PDF reader vulnerability (check for heap spray, ROP chains) or performs a redirect
6. Extract all URLs, IPs, and embedded files as IOCs
7. Classify the sample: exploit (specific CVE) or social engineering (redirect/phishing)
**Pitfalls**:
- Opening the PDF in a standard reader instead of analyzing it with command-line tools
- Missing JavaScript hidden inside Object Streams (/ObjStm) that PDFiD detects but simple parsers miss
- Not decompressing streams before analysis (FlateDecode, ASCIIHexDecode, ASCII85Decode filters)
- Assuming the absence of /JS means no JavaScript; code can be embedded in form fields (/AcroForm with /XFA)
## Output Format
```
PDF MALWARE ANALYSIS REPORT
==============================
File: invoice_2025.pdf
SHA-256: e3b0c44298fc1c149afbf4c8996fb924...
File Size: 45,312 bytes
PDF Version: 1.7
PDFID TRIAGE
/JS: 1 [HIGH RISK]
/JavaScript: 1 [HIGH RISK]
/OpenAction: 1 [HIGH RISK]
/EmbeddedFile: 0
/Launch: 0
/URI: 2
/Page: 1
/ObjStm: 1 [OBFUSCATION]
SUSPICIOUS OBJECTS
Object 5: /OpenAction -> references Object 8
Object 8: /JavaScript stream (FlateDecode, 2,847 bytes decompressed)
Object 12: /ObjStm containing objects 15-18
EXTRACTED JAVASCRIPT
Layer 1: eval(unescape("%68%65%6C%6C%6F"))
Layer 2: var url = "hxxp://malicious[.]com/payload.exe";
app.launchURL(url, true);
// Social engineering redirect, not exploit
EXTRACTED IOCs
URLs: hxxp://malicious[.]com/payload.exe
hxxps://fake-login[.]com/adobe/verify
Domains: malicious[.]com, fake-login[.]com
CLASSIFICATION
Type: Social Engineering (URL redirect)
CVE: None (no exploit code detected)
Risk: HIGH (downloads executable payload)
Family: Generic PDF Dropper
```

119
vendor-new/Anthropic-Cybersecurity-Skills/skills/analyzing-pdf-malware-with-pdfid/references/api-reference.md Normal file
View File

@@ -0,0 +1,119 @@
# API Reference: PDF Malware Analysis Tools
## PDFiD - PDF Keyword Scanner
### Syntax
```bash
pdfid.py document.pdf
pdfid.py -n document.pdf # Show all keywords (including zero counts)
pdfid.py -e document.pdf # Extra data (entropy)
pdfid.py -f document.pdf # Force scan (ignore header)
```
### Suspicious Keywords
| Keyword | Risk | Description |
|---------|------|-------------|
| `/JS` | HIGH | JavaScript code |
| `/JavaScript` | HIGH | JavaScript action |
| `/AA` | HIGH | Additional Actions (auto-execute) |
| `/OpenAction` | HIGH | Action on document open |
| `/Launch` | HIGH | Launch external application |
| `/EmbeddedFile` | MEDIUM | Embedded file object |
| `/AcroForm` | MEDIUM | Interactive form |
| `/JBIG2Decode` | HIGH | JBIG2 exploit vector (CVE-2009-0658) |
| `/RichMedia` | MEDIUM | Flash/multimedia content |
| `/XFA` | MEDIUM | XML Forms (script capable) |
| `/ObjStm` | LOW | Object streams (can hide objects) |
### Output Format
```
PDF Header: %PDF-1.7
obj 45
endobj 45
stream 12
/JS 2
/JavaScript 1
/OpenAction 1
/EmbeddedFile 0
```
## pdf-parser.py - PDF Object Parser
### Syntax
```bash
pdf-parser.py document.pdf # List all objects
pdf-parser.py -o 5 document.pdf # Show object 5
pdf-parser.py -s "/JS" document.pdf # Search for keyword
pdf-parser.py -f document.pdf # Filter streams
pdf-parser.py -c document.pdf # Show raw content
pdf-parser.py -d 5 document.pdf # Dump stream of object 5
pdf-parser.py --object 5 --filter document.pdf # Decompress stream
```
## peepdf - Interactive PDF Analysis
### Syntax
```bash
peepdf -i document.pdf # Interactive mode
peepdf -f document.pdf # Force analysis
peepdf -l document.pdf # Loose mode
```
### Interactive Commands
```
info # Document summary
tree # Object tree
object 5 # Show object
stream 5 # Show stream content
js_analyse # Analyze all JavaScript
extract js > output.js # Extract JavaScript
```
## Known PDF Exploit CVEs
| CVE | Component | Description |
|-----|-----------|-------------|
| CVE-2009-0658 | JBIG2Decode | Buffer overflow in JBIG2 decoder |
| CVE-2009-0927 | Collab.getIcon | JavaScript method exploit |
| CVE-2008-2992 | util.printf | Format string vulnerability |
| CVE-2010-0188 | LibTIFF | TIFF image processing overflow |
| CVE-2013-0640 | XFA | XML Forms Architecture exploit |
| CVE-2018-4990 | EmbeddedFile | Double-free in embedded files |
## YARA Rules for PDF Malware
### Example Rule
```yara
rule PDF_Suspicious {
meta:
description = "PDF with JavaScript and auto-execution"
strings:
$pdf = "%PDF-"
$js = "/JS" nocase
$openaction = "/OpenAction"
$launch = "/Launch"
condition:
$pdf at 0 and ($js and $openaction) or $launch
}
```
## Python PDF Libraries
### PyPDF2
```python
from PyPDF2 import PdfReader
reader = PdfReader("document.pdf")
print(len(reader.pages))
for page in reader.pages:
print(page.extract_text())
```
### pikepdf
```python
import pikepdf
pdf = pikepdf.open("document.pdf")
for obj_num in pdf.objects:
obj = pdf.get_object(obj_num)
if "/JS" in str(obj):
print(f"JavaScript in object {obj_num}")
```

240
vendor-new/Anthropic-Cybersecurity-Skills/skills/analyzing-pdf-malware-with-pdfid/scripts/agent.py Normal file
View File

@@ -0,0 +1,240 @@
#!/usr/bin/env python3
"""PDF malware analysis agent using pdfid concepts and pdf-parser for object extraction."""
import re
import os
import sys
import hashlib
import zlib
def compute_hash(filepath):
"""Compute SHA-256 hash of a file."""
sha256 = hashlib.sha256()
with open(filepath, "rb") as f:
for chunk in iter(lambda: f.read(65536), b""):
sha256.update(chunk)
return sha256.hexdigest()
PDF_SUSPICIOUS_KEYWORDS = {
"/JS": "JavaScript (embedded script execution)",
"/JavaScript": "JavaScript action",
"/AA": "Additional Actions (auto-execute triggers)",
"/OpenAction": "Action on document open",
"/AcroForm": "Interactive form (can contain JavaScript)",
"/JBIG2Decode": "JBIG2 decoder (CVE-2009-0658 exploit vector)",
"/RichMedia": "Rich media / Flash content",
"/Launch": "Launch action (execute external file)",
"/EmbeddedFile": "Embedded file (potential payload)",
"/XFA": "XML Forms Architecture (script execution)",
"/URI": "URI action (external link)",
"/SubmitForm": "Form submission (data exfiltration)",
"/ObjStm": "Object Stream (can hide objects from basic parsers)",
}
def scan_pdf_keywords(filepath):
"""Scan a PDF file for suspicious keywords similar to pdfid."""
with open(filepath, "rb") as f:
data = f.read()
text = data.decode("latin-1", errors="replace")
results = {}
for keyword, description in PDF_SUSPICIOUS_KEYWORDS.items():
count = text.count(keyword)
if count > 0:
results[keyword] = {"count": count, "description": description}
# Count standard PDF structure elements
structure = {
"obj": len(re.findall(r"\d+ \d+ obj", text)),
"endobj": text.count("endobj"),
"stream": text.count("stream"),
"endstream": text.count("endstream"),
"xref": text.count("xref"),
"trailer": text.count("trailer"),
"startxref": text.count("startxref"),
"page_count": len(re.findall(r"/Type\s*/Page[^s]", text)),
"encrypted": 1 if "/Encrypt" in text else 0,
}
return results, structure
def extract_pdf_version(filepath):
"""Extract the PDF version from the header."""
with open(filepath, "rb") as f:
header = f.read(20)
match = re.search(rb"%PDF-(\d+\.\d+)", header)
return match.group(1).decode() if match else "unknown"
def find_stream_objects(filepath):
"""Find and extract stream objects from the PDF."""
with open(filepath, "rb") as f:
data = f.read()
streams = []
pattern = rb"(\d+)\s+(\d+)\s+obj.*?stream\r?\n(.*?)endstream"
for match in re.finditer(pattern, data, re.DOTALL):
obj_num = int(match.group(1))
gen_num = int(match.group(2))
stream_data = match.group(3)
decoded = None
try:
decoded = zlib.decompress(stream_data)
except zlib.error:
pass
streams.append({
"object": f"{obj_num} {gen_num}",
"raw_size": len(stream_data),
"decoded_size": len(decoded) if decoded else 0,
"decodable": decoded is not None,
"preview": (decoded[:200] if decoded else stream_data[:200]).decode(
"latin-1", errors="replace"),
})
return streams
def extract_javascript(filepath):
"""Extract JavaScript code from PDF objects."""
with open(filepath, "rb") as f:
data = f.read()
text = data.decode("latin-1", errors="replace")
js_blocks = []
# Look for JavaScript in stream objects
js_pattern = re.compile(r"/JS\s*\((.*?)\)", re.DOTALL)
for match in js_pattern.finditer(text):
js_blocks.append({"type": "inline", "code": match.group(1)[:500]})
# Look for JavaScript in hex-encoded strings
hex_pattern = re.compile(r"/JS\s*<([0-9A-Fa-f]+)>")
for match in hex_pattern.finditer(text):
try:
decoded = bytes.fromhex(match.group(1)).decode("utf-8", errors="replace")
js_blocks.append({"type": "hex_encoded", "code": decoded[:500]})
except ValueError:
pass
return js_blocks
def extract_urls(filepath):
"""Extract URLs from the PDF content."""
with open(filepath, "rb") as f:
data = f.read()
text = data.decode("latin-1", errors="replace")
urls = list(set(re.findall(r"https?://[^\s<>\"')\]]+", text)))
return urls
def detect_exploits(keywords, streams):
"""Check for known PDF exploit indicators."""
exploits = []
if "/JBIG2Decode" in keywords:
exploits.append({
"cve": "CVE-2009-0658",
"description": "JBIG2 decoder vulnerability in Adobe Reader",
"confidence": "MEDIUM",
})
for stream in streams:
preview = stream.get("preview", "").lower()
if "shellcode" in preview or "\\x90\\x90" in preview:
exploits.append({
"cve": "Generic shellcode",
"description": "Potential shellcode detected in stream",
"confidence": "HIGH",
})
if "util.printf" in preview or "collab.geticon" in preview:
exploits.append({
"cve": "CVE-2008-2992 / CVE-2009-0927",
"description": "Known Adobe Reader JavaScript exploits",
"confidence": "HIGH",
})
return exploits
def calculate_risk_score(keywords, structure, exploits, js_blocks):
"""Calculate a risk score for the PDF."""
score = 0
if "/JS" in keywords or "/JavaScript" in keywords:
score += 30
if "/OpenAction" in keywords or "/AA" in keywords:
score += 20
if "/Launch" in keywords:
score += 25
if "/EmbeddedFile" in keywords:
score += 15
if "/JBIG2Decode" in keywords:
score += 20
if structure.get("encrypted"):
score += 10
score += len(exploits) * 20
score += len(js_blocks) * 10
return min(score, 100)
def generate_report(filepath, keywords, structure, streams, js_blocks,
urls, exploits, risk_score):
"""Generate PDF malware analysis report."""
return {
"file": filepath,
"sha256": compute_hash(filepath),
"size": os.path.getsize(filepath),
"pdf_version": extract_pdf_version(filepath),
"structure": structure,
"suspicious_keywords": keywords,
"streams": len(streams),
"javascript_blocks": len(js_blocks),
"urls_found": len(urls),
"exploit_indicators": exploits,
"risk_score": risk_score,
"risk_level": "HIGH" if risk_score >= 60 else "MEDIUM" if risk_score >= 30 else "LOW",
}
if __name__ == "__main__":
print("=" * 60)
print("PDF Malware Analysis Agent")
print("Keyword scanning, JavaScript extraction, exploit detection")
print("=" * 60)
target = sys.argv[1] if len(sys.argv) > 1 else None
if target and os.path.exists(target):
print(f"\n[*] Analyzing: {target}")
print(f"[*] SHA-256: {compute_hash(target)}")
print(f"[*] PDF version: {extract_pdf_version(target)}")
print("\n--- Suspicious Keywords (pdfid-style) ---")
keywords, structure = scan_pdf_keywords(target)
for kw, info in keywords.items():
print(f" [!] {kw}: {info['count']}x - {info['description']}")
print(f"\n--- Structure ---")
for key, val in structure.items():
print(f" {key}: {val}")
print("\n--- Stream Objects ---")
streams = find_stream_objects(target)
print(f" Found: {len(streams)} streams")
print("\n--- JavaScript Extraction ---")
js = extract_javascript(target)
for j in js:
print(f" [{j['type']}] {j['code'][:100]}...")
print("\n--- URLs ---")
urls = extract_urls(target)
for u in urls[:10]:
print(f" {u}")
print("\n--- Exploit Detection ---")
exploits = detect_exploits(keywords, streams)
for e in exploits:
print(f" [{e['confidence']}] {e['cve']}: {e['description']}")
risk = calculate_risk_score(keywords, structure, exploits, js)
print(f"\n[*] Risk Score: {risk}/100")
else:
print(f"\n[DEMO] Usage: python agent.py <document.pdf>")