book-market-research
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which could potentially contain malicious instructions. \n- Ingestion points: The skill ingests user-provided 'Book Concept Documents', 'Validation Reports', and competitor data via a CSV file. It also performs web searches to gather qualitative data on competitors and reader reviews from external websites. \n- Boundary markers: There are no explicit instructions or delimiters defined in the skill to separate user-provided content or web search results from the agent's core instructions, increasing the risk of the agent following instructions found within those documents. \n- Capability inventory: The agent's capabilities are limited to web searching and generating markdown and CSV reports. It does not have access to arbitrary code execution, system-level file modification, or non-search network operations. \n- Sanitization: The skill lacks explicit sanitization or filtering instructions for data retrieved from external web sources or user-uploaded files.
Audit Metadata