microservices

Warn

Audited by Gen Agent Trust Hub on Apr 7, 2026

Risk Level: MEDIUMCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill contains instructions for the AI agent to perform automated filesystem probing using the ls command.
  • Evidence: In SKILL.md, the 'Companion check' section directs the agent to 'check which companion skills are installed by running ls ~/.claude/skills/ ~/.agent/skills/ ~/.agents/skills/ .claude/skills/ .agent/skills/ .agents/skills/ 2>/dev/null'.
  • Context: While the stated purpose is to recommend related skills from the same vendor, this pattern involves executing shell commands to gather information about the user's environment without explicit triggering from the user's immediate request.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 7, 2026, 03:04 PM
Security Audit — agent-trust-hub — microservices