review-hog-authoring

Pass

Audited by Gen Agent Trust Hub on Jul 17, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses vendor-specific tools (posthog:skill-create, posthog:skill-update) to programmatically manage AI agent skills on the PostHog platform. This behavior is the primary intended purpose of the authoring guide.
  • [EXTERNAL_DOWNLOADS]: The skill retrieves and references existing platform skill definitions using posthog:skill-list and posthog:skill-get to provide context and structural examples for the user.
  • [PROMPT_INJECTION]: The skill describes an authoring workflow that accepts user input to generate new skill instructions. This 'skill factory' pattern is restricted to the platform's internal management tools and does not involve bypassing security controls.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 17, 2026, 10:10 AM
Security Audit — agent-trust-hub — review-hog-authoring