melech-sync-skills

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). The skill instructs the agent to run npx skills add to fetch and install skills from a GitHub repository, which exposes the agent to outsider-authored skill definitions and metadata.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs the agent to execute an external GitHub repository (AdirD/agent-shell-hamelech) via the Vercel Skills CLI at runtime, which constitutes an unofficial third-party operational dependency.