employment-law

Warn

Audited by Gen Agent Trust Hub on Apr 7, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions in SKILL.md (Companion check section) direct the agent to execute a shell command (ls) to inspect hidden directories in the user's home path (~/.claude/skills/, ~/.agent/skills/, etc.) to identify installed companion skills.
  • [REMOTE_CODE_EXECUTION]: The skill contains instructions for the agent to suggest and potentially execute npx skills add commands. This involves downloading and executing packages from the npm registry, which constitutes a remote code execution vector.
  • [EXTERNAL_DOWNLOADS]: Both the primary installation instructions in README.md and the companion check logic in SKILL.md facilitate the download of external components through npx commands and references to external repositories.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 7, 2026, 03:03 PM
Security Audit — agent-trust-hub — employment-law