analyzing-malicious-pdf-with-peepdf
Perform static analysis of malicious PDF documents using peepdf, pdfid, and pdf-parser to extract embedded JavaScript, shellcode, and suspicious objects.
66
58%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/analyzing-malicious-pdf-with-peepdf/SKILL.mdQuality
Discovery
82%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong, specific description that clearly identifies a niche domain (malicious PDF forensic analysis) with concrete tools and actions. Its main weakness is the absence of an explicit 'Use when...' clause, which would help Claude know exactly when to select this skill. The technical specificity and tool names make it highly distinctive.
Suggestions
Add a 'Use when...' clause such as 'Use when the user asks to analyze suspicious or malicious PDFs, investigate PDF-based malware, or extract embedded payloads from PDF documents.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'static analysis of malicious PDF documents', 'extract embedded JavaScript, shellcode, and suspicious objects', and names specific tools (peepdf, pdfid, pdf-parser). | 3 / 3 |
Completeness | Clearly answers 'what does this do' (static analysis of malicious PDFs, extracting embedded content) but lacks an explicit 'Use when...' clause or equivalent trigger guidance, which caps this at 2 per the rubric. | 2 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'malicious PDF', 'static analysis', 'JavaScript', 'shellcode', 'suspicious objects', plus specific tool names (peepdf, pdfid, pdf-parser) that users familiar with the domain would reference. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche: malicious PDF analysis with specific forensic/security tools. Very unlikely to conflict with general PDF processing skills or other security skills due to the specific tool names and malware analysis focus. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a reasonable high-level framework for malicious PDF analysis but critically lacks executable commands and concrete code examples, making it more of a conceptual overview than an actionable skill. The workflow is well-sequenced but missing validation checkpoints and specific tool invocations. The explanatory tables add token cost without proportional value for Claude.
Suggestions
Add concrete, executable command examples for each workflow step (e.g., `pdfid.py malicious.pdf`, `peepdf -i malicious.pdf`, `PPDF> object 5` to extract a suspicious object).
Include a complete worked example showing the analysis of a sample malicious PDF from triage through IOC extraction, with actual tool output.
Add validation checkpoints to the workflow, such as verifying extracted JS is syntactically valid before deobfuscation, or confirming sandbox isolation before opening the PDF.
Remove or significantly condense the Key Concepts table—Claude already knows what FlateDecode and /OpenAction are—and replace with tool-specific syntax that Claude may not know.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The key concepts table explains PDF-specific terms that Claude likely already knows (e.g., FlateDecode, /OpenAction). The tools table is somewhat redundant given the prerequisites section. However, the workflow and output format sections are reasonably tight. | 2 / 3 |
Actionability | There are no executable commands or code examples anywhere in the skill. The workflow describes steps abstractly ('Open PDF in peepdf interactive mode', 'Dump suspicious streams') without showing actual commands like `peepdf -i malicious.pdf` or `pdfid.py malicious.pdf`. This is entirely descriptive rather than instructive. | 1 / 3 |
Workflow Clarity | The 7-step workflow provides a clear sequence for the analysis process, but it lacks validation checkpoints and feedback loops. For example, there's no guidance on what to do if pdfid finds nothing suspicious, or how to verify that extracted JavaScript is complete. Given this involves potentially dangerous malware analysis, missing safety validation steps are notable. | 2 / 3 |
Progressive Disclosure | The content is organized into logical sections (workflow, key concepts, tools, output format), but everything is inline in a single file with no references to external resources for deeper topics like JavaScript deobfuscation techniques or shellcode analysis. The key concepts and tools tables could be separate reference files, keeping the main skill leaner. | 2 / 3 |
Total | 7 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- mukul975/Anthropic-Cybersecurity-Skills
- Commit
c15f73d
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.