pdf-skill

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
  • [No Code] (SAFE): The skill consists exclusively of a documentation file (SKILL.md) and contains no executable scripts, binaries, or configuration files.
  • [Indirect Prompt Injection] (LOW): The skill describes workflows for parsing external and potentially untrusted PDF documents, which serves as a surface for indirect prompt injection.
  • Ingestion points: Extraction of text and data from external PDF files (Workflow 3 in SKILL.md).
  • Boundary markers: None; the skill does not suggest the use of delimiters or 'ignore' instructions for the parsed content.
  • Capability inventory: The documentation references tools with file-writing (PDFKit) and network-access (Puppeteer/Playwright) capabilities.
  • Sanitization: No sanitization or validation steps are provided for the extracted data.
  • [External Downloads] (SAFE): The skill recommends the installation of well-known, legitimate libraries from standard registries (npm, PyPI) such as PDFKit and Puppeteer. No suspicious or unverified sources are referenced.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:20 PM