working-with-skills

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill consists entirely of instructional Markdown documentation. It serves as a decision tree and workflow guide for using external PostHog MCP tools and does not contain any functional logic or executable code.
  • [NO_CODE]: No scripts, packages, or binary files are bundled with this skill. It defines usage patterns but does not implement them through code.
  • [SAFE]: The skill includes explicit security best practices, such as warning agents against over-declaring tools in their manifests (identifying it as a "security smell") and promoting progressive disclosure to minimize context pollution.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 03:33 PM
Security Audit — agent-trust-hub — working-with-skills