Skills
Navigate
skills/autohandai/community-skills/analyzing-malicious-pdf-with-peepdf/Gen Agent Trust Hub

analyzing-malicious-pdf-with-peepdf

Warn

Audited by Gen Agent Trust Hub on Jul 16, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/agent.py uses subprocess.run to call external PDF analysis tools such as peepdf, pdfid, and pdf-parser.py. The input file path for these commands is provided by the user via command-line arguments.
  • [EXTERNAL_DOWNLOADS]: The documentation in SKILL.md and references/api-reference.md provides instructions for the user to install dependencies, including the peepdf-3 package via pip and the peepdf repository from GitHub.
  • [PROMPT_INJECTION]: The skill processes untrusted content from PDF files which may contain malicious instructions designed to exploit the analysis tools or influence the agent's interpretation of results.
  • Ingestion points: PDF content is read and analyzed in scripts/agent.py to extract objects and metadata.
  • Boundary markers: There are no explicit markers or instructions to the agent to ignore potentially malicious embedded text.
  • Capability inventory: The skill has the ability to execute shell commands via subprocess and write files to the local system.
  • Sanitization: Content extraction is performed via regular expressions, but the results are not sanitized or escaped before being included in the final analysis report.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 16, 2026, 04:55 PM
Security Audit — agent-trust-hub — analyzing-malicious-pdf-with-peepdf