translate-pdf

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external PDF documents, which could contain instructions intended to influence the agent's behavior during the translation process.
  • Ingestion points: Text is extracted from user-supplied PDF files via scripts/extract_texts.py.
  • Boundary markers: The workflow does not implement specific delimiters or 'ignore' instructions for the extracted text when it is reviewed by the agent.
  • Capability inventory: The skill performs file system reads and writes (PDF and JSON) and executes local scripts.
  • Sanitization: No sanitization is performed on the text extracted from the PDF before processing.
  • [COMMAND_EXECUTION]: The skill workflow involves executing local Python scripts to extract text and generate the translated PDF. These commands are necessary for the skill's functionality.
  • [EXTERNAL_DOWNLOADS]: The scripts depend on the pymupdf Python library. While the library itself is a standard tool for PDF manipulation, it requires installation from an external package registry.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 06:10 AM