skill-teaching

Pass

Audited by Gen Agent Trust Hub on Jun 21, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses a bash script (scripts/sync-skills.sh) to perform file system operations.
  • Evidence: The script uses cp -R, rm -rf, mkdir -p, and jq to manage local skill directories and sync manifests.
  • Context: The operations are limited to project-specific directories (.claude/skills, .codex/skills, etc.) and the official Claude plugin cache in the user's home directory. This is consistent with the skill's stated purpose of synchronizing agent capabilities.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 21, 2026, 03:28 PM
Security Audit — agent-trust-hub — skill-teaching