web-scanning

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

• Third-party content exposure detected (high risk: 1.00). The skill's workflow explicitly instructs fetching and crawling arbitrary public URLs (e.g., "npx @axe-core/cli ", capture-website-cli "", "curl -s <BASE_URL>/sitemap.xml", and link-based crawling rules) and uses the fetched page content to drive scanning and crawling decisions, exposing the agent to untrusted third-party content that can influence tool actions.