ocr-book-polisher
Pass
Audited by Gen Agent Trust Hub on Oct 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No security issues detected. The skill instructions focus on document processing, OCR correction, and typesetting using established tools like XeLaTeX, Pandoc, and various OCR engines.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from PDFs and OCR outputs. This represents a standard ingestion surface. The instructions mitigate this by requiring the agent to treat OCR as suspect, perform spot checks against source evidence, and validate the final output against structural maps.
Audit Metadata