iyeque-pdf-reader

Pass

Audited by Gen Agent Trust Hub on Apr 7, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted PDF documents for text extraction, creating a surface for indirect prompt injection.
  • Ingestion points: Untrusted data enters the agent context through PDF files specified via the file_path parameter in SKILL.md.
  • Boundary markers: The skill instructions do not define delimiters or specific warnings to differentiate extracted text from system instructions.
  • Capability inventory: The skill performs local file reads and metadata extraction using fitz (PyMuPDF); no network or write operations are documented in the provided structure.
  • Sanitization: No sanitization or filtering of the extracted text content is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 7, 2026, 01:20 AM
Security Audit — agent-trust-hub — iyeque-pdf-reader