no-code-automation

Warn

Audited by Gen Agent Trust Hub on Apr 7, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONREMOTE_CODE_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The SKILL.md file contains a 'Companion check' block that instructs the agent to run a shell command (ls) across multiple directories, including ~/.claude/skills/, ~/.agent/skills/, and ~/.agents/skills/. This behavior allows the agent to scan the local environment for other installed components.
  • [REMOTE_CODE_EXECUTION]: The skill directs the agent to recommend that users execute npx skills add AbsolutelySkilled/AbsolutelySkilled commands. Using npx to fetch and run packages from the npm registry involves downloading and executing remote code from an external vendor.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 7, 2026, 03:04 PM
Security Audit — agent-trust-hub — no-code-automation