nano-pdf

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection attacks where malicious instructions could be embedded in the processed documents.
  • Ingestion points: Untrusted PDF files provided by the user (e.g., deck.pdf in SKILL.md).
  • Boundary markers: None present. The instructions do not specify delimiters or warnings to ignore instructions embedded within the PDF content.
  • Capability inventory: The skill can modify files on the local system using the nano-pdf CLI (SKILL.md).
  • Sanitization: No sanitization or filtering of the PDF input content is described or implemented.
  • [EXTERNAL_DOWNLOADS]: The skill downloads and installs the nano-pdf package from the Python Package Index (PyPI) during setup. This is a standard installation procedure for the tool's core functionality.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 12:13 AM