pdf-extract

Pass

Audited by Gen Agent Trust Hub on Aug 16, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill extracts text from external PDF files, creating a surface for indirect prompt injection where malicious instructions embedded in a document could influence the agent. * Ingestion points: SKILL.md uses page.get_text() to read content from PDF files. * Boundary markers: The instructions do not include markers or warnings to treat the extracted content as untrusted data. * Capability inventory: The skill possesses Bash and Write capabilities to execute logic and interact with the file system. * Sanitization: There is no evidence of filtering or sanitization of the extracted PDF text.
  • [COMMAND_EXECUTION]: The skill performs its operations by executing Python code snippets directly through the bash command line using uv run and python3 -c.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 16, 2026, 01:32 AM
Security Audit — agent-trust-hub — pdf-extract