Skills
Navigate
skills/redfox-data/redfox-community/pdf-image-text-extractor/Gen Agent Trust Hub

pdf-image-text-extractor

Pass

Audited by Gen Agent Trust Hub on Sep 11, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted PDF and image documents which serve as ingestion points for external data.
  • Ingestion points: Documents are processed by the read_image tool and the scripts/pdf_text_extractor.py script as defined in SKILL.md.
  • Boundary markers: The instructions do not define clear delimiters or specific instructions for the agent to treat extracted text as data rather than instructions.
  • Capability inventory: The skill has the capability to execute local scripts and use vision tools to interpret content.
  • Sanitization: No sanitization is performed on the extracted text to filter out potential malicious instructions embedded in the documents.
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the pymupdf library, which is a widely recognized and standard package for PDF manipulation.
  • [COMMAND_EXECUTION]: The skill's workflow in SKILL.md involves the execution of a local Python script (scripts/pdf_text_extractor.py) using the command line to process PDF files.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 11, 2026, 04:51 AM
Security Audit — agent-trust-hub — pdf-image-text-extractor