openspec-explore
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security risks were detected in the skill instructions. The tool is designed for exploratory discussion and explicitly states that no artifacts or files are created during use.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to analyze the local codebase, which is an ingestion point for untrusted data. However, the risk is minimal as the skill's capabilities are restricted to conversational insights. 1. Ingestion points: Local project codebase. 2. Boundary markers: None specified. 3. Capability inventory: Limited to conversational output; the skill explicitly prohibits the creation of files or artifacts. 4. Sanitization: Not specified.
Audit Metadata