clean-code

Fail

Audited by Gen Agent Trust Hub on Aug 10, 2026

Risk Level: HIGHCOMMAND_EXECUTIONREMOTE_CODE_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill contains instructions for the agent to list contents of multiple hidden directories in the user's home folder to identify installed software.
  • Evidence: ls ~/.claude/skills/ ~/.agent/skills/ ~/.agents/skills/ .claude/skills/ .agent/skills/ .agents/skills/ 2>/dev/null (found in SKILL.md).
  • [REMOTE_CODE_EXECUTION]: The instructions direct the agent to autonomously offer and execute the installation of external code from a third-party repository.
  • Evidence: npx skills add AbsolutelySkilled/AbsolutelySkilled --skill <name> (found in SKILL.md and README.md).
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Aug 10, 2026, 02:05 PM
Security Audit — agent-trust-hub — clean-code