diagnosing-missing-recordings
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious instructions, hidden code, or unauthorized network operations were detected. The skill uses vendor-specific tools for their intended diagnostic purposes and follows legitimate troubleshooting workflows.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it is designed to ingest and interpret data from external database queries.
- Ingestion points: Session and event property data are retrieved from PostHog via
posthog:execute-sqlandposthog:session-recording-get(SKILL.md). - Boundary markers: The instructions do not define specific delimiters or warnings to ignore potential instructions embedded within the queried data results.
- Capability inventory: The skill utilizes
posthog:execute-sql,posthog:session-recording-get, andposthog:query-session-recordings-listto perform diagnostics. - Sanitization: No specific sanitization or filtering logic is provided for the data returned from the tool calls before it is processed by the agent. This is an inherent surface for diagnostic tools, and in this context, it is considered safe due to the skill's primary purpose.
Audit Metadata