idea-research
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from the open web using a search tool, which introduces a surface for indirect prompt injection if a website contains hidden instructions intended to manipulate the agent.
- Ingestion points: External content retrieved via the
WebSearchtool as specified in the skill instructions. - Boundary markers: The prompt does not define specific delimiters or "ignore instructions" wrappers for the content fetched from the web.
- Capability inventory: The skill is restricted to research and reporting facts; it does not utilize file system writes, shell commands, or arbitrary network requests outside of the search function.
- Sanitization: No explicit sanitization or filtering logic is provided to handle potentially malicious content within search results.
Audit Metadata