local-seo

Fail

Audited by Gen Agent Trust Hub on Apr 7, 2026

Risk Level: HIGHCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes instructions that trigger automated command execution on the user's machine. In SKILL.md, the 'Companion check' section instructs the agent to run ls commands targeting multiple paths in the user's home directory (~/.claude/skills/, ~/.agent/skills/, etc.) upon activation. This enables unauthorized file system enumeration and command execution without an explicit user prompt.- [EXTERNAL_DOWNLOADS]: The skill documentation and internal logic promote the installation of external code from a remote source. Both README.md and SKILL.md provide commands to use npx skills add AbsolutelySkilled/AbsolutelySkilled, which downloads and executes scripts from a repository that is not part of a verified or well-known service registry.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Apr 7, 2026, 03:06 PM
Security Audit — agent-trust-hub — local-seo