book-research
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves book reviews, author biographies, and descriptions from external platforms (Goodreads, Apple Books, and Audible). This content is user-generated and could potentially contain instructions aimed at influencing the agent's behavior. \n
- Ingestion points: API responses from api.crawlora.net containing reviews, description, bio, and quotes.\n
- Boundary markers: There are no explicit markers or instructions to the agent to disregard commands within the fetched data.\n
- Capability inventory: The skill utilizes scripts/crawlora.sh to make network requests to the Crawlora API.\n
- Sanitization: The skill's helper script performs robust validation on paths and credentials but does not sanitize the contents of the returned API data.
Audit Metadata