skill-suggest

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

• Third-party content exposure detected (low risk: 0.10). The workflow ingests search results from the public skills.sh API (https://skills.sh/api/search), which contains third-party registry item descriptions and metadata authored by outsiders.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill queries the skills.sh registry API and executes skill installations via npm/npx without an explicit remote repository locator defining a trusted first-party package source, representing a weak operational dependency.