skills/pwguler/skills/which-skill/Gen Agent Trust Hub

which-skill

Pass

Audited by Gen Agent Trust Hub on Aug 5, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill is composed entirely of natural language instructions in markdown format and does not include any scripts, binaries, or executable code.
  • [SAFE]: The skill uses a filesystem glob pattern (*/SKILL.md) to discover other skills in the same directory. This is a read-only metadata discovery process intended to support its primary function as a router.
  • [SAFE]: While the skill instructs the agent to treat local files as a 'source of truth' over its internal registry, this behavior is documented as a way to find intentionally hidden skills and does not involve bypassing security controls.
  • [SAFE]: Mentions of utilities such as spawn or write-skill refer to external triggers or separate skills and do not represent capabilities or logic contained within this specific skill file.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 5, 2026, 07:05 PM
Security Audit — agent-trust-hub — which-skill