seed-concept-search
Pass
Audited by Gen Agent Trust Hub on Jun 23, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill defines a standard operating procedure for concept searching using internal vault searches and web search tools. No code or commands are executed.
- [NO_CODE]: No scripts or binaries are provided with the skill.
- [PROMPT_INJECTION]: The skill ingests data from vault and web sources, representing a surface for indirect prompt injection. 1. Ingestion points: vault_search and brave-search. 2. Boundary markers: None. 3. Capability inventory: None (only search tools). 4. Sanitization: None.
Audit Metadata