finding-sessions-to-watch

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes posthog:execute-sql to retrieve specific session identifiers. The instructions provide safe query templates limited to analytical filtering by event type and timestamp.
  • [INDIRECT_PROMPT_INJECTION]: The skill handles untrusted data by ingesting event names and property values from the database to build recording filters.
  • Ingestion points: Data returned by posthog:read-data-schema and posthog:query-session-recordings-list.
  • Boundary markers: Not explicitly defined in the instructions.
  • Capability inventory: Database querying via posthog:execute-sql and playlist creation via posthog:session-recording-playlist-create.
  • Sanitization: The instructions mandate confirming schema details using read-data-schema before interpolation, which serves as a validation step.
  • [DATA_EXFILTRATION]: Access to session data is managed through authorized vendor tools within the expected scope of the platform. Links generated follow official deep-linking patterns to the vendor's own domains.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 09:40 AM
Security Audit — agent-trust-hub — finding-sessions-to-watch