on-site-seo

Pass

Audited by Gen Agent Trust Hub on Apr 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to perform directory listing using the ls command on multiple paths (e.g., ~/.claude/skills/, ~/.agent/skills/, and .agents/skills/) during its first activation. This is intended to discover if recommended companion skills (like technical-seo or core-web-vitals) are already installed to provide better integration.
  • [EXTERNAL_DOWNLOADS]: The documentation references the installation of external development packages and tools, such as the astro-seo npm package and the @nuxtjs/seo module, which are standard for the skill's stated purpose of implementing SEO in modern web frameworks.
  • [DATA_EXPOSURE_AND_EXFILTRATION]: While the skill accesses file paths to check for installed skills, no network requests to external or non-whitelisted domains were detected in the instructions or scripts, and no sensitive data (such as credentials or user tokens) is targeted for extraction.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 7, 2026, 03:03 PM
Security Audit — agent-trust-hub — on-site-seo