reading-books
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external document formats (PDF, EPUB, MOBI, TXT) which represent a surface for indirect prompt injection. Malicious instructions embedded in a book's text could attempt to influence the agent's behavior when the content is read or searched.\n
- Ingestion points: File reading and text extraction logic in
book.pyfor all supported book formats.\n - Capability inventory: The skill returns extracted text to the agent; the script itself performs local file reading and caching without network access or privileged operations.\n
- Boundary markers: Text extracted from books is provided to the agent without explicit delimiters or instructions to ignore potential commands embedded in the data.\n
- Sanitization: There is no sanitization or filtering of the extracted text content to remove or neutralize prompt injection attempts.
Audit Metadata