pdf-reader

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted PDF files which can contain embedded instructions designed to influence the agent's behavior (Indirect Prompt Injection).
  • Ingestion points: The reader.py script reads file content via pymupdf.open(file_path) from the local filesystem.
  • Boundary markers: The skill does not implement delimiters or specific instructions for the agent to ignore embedded commands within the extracted text.
  • Capability inventory: The skill provides text extraction and metadata retrieval capabilities from files using the pymupdf library.
  • Sanitization: No sanitization or filtering of the extracted text is performed before returning it to the agent.
  • [EXTERNAL_DOWNLOADS]: The skill installs the PyMuPDF package from the standard Python package registry to handle PDF processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 07:46 PM
Security Audit — agent-trust-hub — pdf-reader