posthog-data-handling

Pass

Audited by Gen Agent Trust Hub on Mar 24, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [SAFE]: No malicious patterns or security risks were detected in the skill's instructions or implementation examples.
  • [EXTERNAL_DOWNLOADS]: The skill uses fetch to interact with official PostHog API endpoints (us.i.posthog.com) for tasks such as data deletion and querying. These references target a well-known service and are consistent with the skill's stated purpose.
  • [CREDENTIALS_UNSAFE]: The implementation patterns correctly handle sensitive information by referencing environment variables (e.g., POSTHOG_PERSONAL_API_KEY, POSTHOG_PROJECT_ID) instead of using hardcoded secrets.
  • [PROMPT_INJECTION]: The skill templates for data lookups and exports interpolate identifiers into URLs and HogQL queries. While this creates a potential surface for indirect injection if processing untrusted data, the logic is provided as a standard implementation pattern for compliance workflows.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 24, 2026, 05:30 PM