signals-scout-session-replay
Pass
Audited by Gen Agent Trust Hub on Aug 4, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, unauthorized command execution, or persistence mechanisms were detected. The skill's operations are confined to analyzing PostHog analytics data using platform-provided tools.
- [SAFE]: The skill includes a dedicated security section ('Untrusted data — session content is user-supplied') that explicitly instructs the agent to treat external content such as URLs, element text, and AI summaries as untrusted data rather than instructions. This follows defensive best practices for preventing prompt injection.
- [SAFE]: The SQL queries are well-structured for the PostHog environment and include 'footgun' warnings to ensure accurate and safe data retrieval without excessive resource consumption.
Audit Metadata