Pass
Audited by Gen Agent Trust Hub on Feb 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides documentation for standard PDF manipulation libraries and command-line tools. No malicious behavior or high-risk patterns were detected.
- [PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted PDF content, creating a surface for indirect prompt injection. This is a common property of document processing tools.
- Ingestion points: PDF file reading using pypdf and pdfplumber in SKILL.md.
- Boundary markers: Not present.
- Capability inventory: File writing (writer.write) and CLI tool usage (qpdf, pdftk).
- Sanitization: Not present in the provided examples.
Audit Metadata