skills-discovery

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

• Third-party content exposure detected (low risk: 0.10). The skill searches a public registry API and ingests community-published skill metadata (names and descriptions), falling under low risk.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill queries an API and uses an installer tool from claude-plugins.dev, which is an unverified third-party domain and registry, making it a weak external operational dependency.