feature-usage-feed

Pass

Audited by Gen Agent Trust Hub on Apr 27, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: Employs posthog:execute-sql for database inspection to identify feature prefixes and verify event volume.
  • [DATA_EXFILTRATION]: Facilitates the automated transfer of summarized trace data from PostHog's internal analytics environment to external Slack channels via the PostHog Workflows system.
  • [PROMPT_INJECTION]: Identifies an indirect prompt injection surface where untrusted data from user-generated $ai_generation traces is processed by an LLM-judge for notification summaries. Ingestion points are the trace data fetched via posthog:query-llm-traces-list. Boundary markers and sanitization steps are absent from the prompt template. Capability inventory includes evaluation management and Slack dispatch via PostHog's internal systems.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 27, 2026, 06:45 PM