inbox-exploration

Pass

Audited by Gen Agent Trust Hub on May 11, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill uses a set of read-only tools (inbox-reports-list, inbox-reports-retrieve, inbox-source-configs-list, inbox-source-configs-retrieve) to access PostHog platform data. No write operations or administrative modifications are exposed.
  • [SAFE]: All external links and service references target the vendor's official domain (posthog.com), which is used for documentation and legitimate setup instructions for the PostHog Code product.
  • [SAFE]: The instructions include best-practice workflows, such as verifying the project configuration before attempting to retrieve data, ensuring the agent provides accurate context to the user.
  • [SAFE]: The use of the posthog:execute-sql tool is documented as a way to perform HogQL queries on underlying signal data, which is an expected analytical function of the PostHog integration.
Audit Metadata
Risk Level
SAFE
Analyzed
May 11, 2026, 09:58 PM
Security Audit — agent-trust-hub — inbox-exploration