signals-scout-replay-vision
Pass
Audited by Gen Agent Trust Hub on Jun 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill utilizes legitimate, platform-specific MCP tools for data retrieval and reporting within the PostHog environment. No unauthorized external network activity or code execution was detected.
- [PROMPT_INJECTION]: The skill addresses potential indirect prompt injection risks by including a specific section on handling untrusted data. It instructs the agent to treat scanner outputs as data points rather than instructions and to sanitize identifiers before storage in internal memory.
Audit Metadata