querying-posthog-data

Pass

Audited by Gen Agent Trust Hub on May 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists entirely of documentation, architectural schemas, and HogQL (SQL variant) query templates. No executable scripts, remote downloads, or persistence mechanisms are included.
  • [COMMAND_EXECUTION]: The instructions suggest the agent utilize local shell utilities (such as bash, grep, or jq) to process and explore large query results after dumping them to files. This is presented as a usability recommendation for handling high-cardinality analytics data and relies on the security of the agent's host environment.
  • [PROMPT_INJECTION]: No instructions were found that attempt to bypass AI safety guidelines or override system behavior. The skill includes security-conscious instructions, such as advising the agent not to echo temporary download URLs back to the user.
  • [DATA_EXPOSURE]: While the skill facilitates querying system metadata, the documentation explicitly notes that sensitive fields like encrypted credentials and tokens are excluded from the accessible schemas.
Audit Metadata
Risk Level
SAFE
Analyzed
May 17, 2026, 02:59 PM
Security Audit — agent-trust-hub — querying-posthog-data