pentest

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

• Third-party content exposure detected (high risk: 0.80). This skill explicitly instructs the agent to fetch and parse external, potentially public API/docs and web content (e.g., "Pull OpenAPI or Swagger documents when exposed" in references/api-security-workflows.md and client-side workflows that generate/consume PoC HTML), which are untrusted third-party sources the agent must read and that can materially influence subsequent tool selection and actions.