brainstorm-ideas-existing
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which could contain malicious instructions.
- Ingestion points: Processes user-provided research files and web search content.
- Boundary markers: Lacks explicit delimiters or instructions for the agent to ignore commands within ingested data.
- Capability inventory: Includes web search and workspace file-writing capabilities.
- Sanitization: No sanitization or validation of external content is performed.
Audit Metadata