ask
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWPROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION] (LOW): The skill reads from local vault directories which may contain untrusted data. Evidence: 1. Ingestion points:
30_Research/and40_Wiki/via search. 2. Boundary markers: Absent. 3. Capability inventory: File reading and local wiki note creation. 4. Sanitization: Absent. Severity is LOW as the agent's capabilities are restricted to local file operations with no network access. - [NO_CODE] (INFO): The skill contains only instructions and no executable code, reducing the risk of technical exploits.
Audit Metadata