security-dependency-scanning

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

• Third-party content exposure detected (high risk: 1.00). The skill requires fetching and parsing arbitrary public websites and resources using the WebFetch tool or curl (e.g., "WebFetch tool: url: 'https://example.com'" and instructions to parse HTML, CDN URLs, feeds and fetched files), so the agent will ingest untrusted third-party content as part of its workflow.