architecture-doc-generator

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

• Third-party content exposure detected (high risk: 0.80). The skill's required workflow explicitly instructs the agent to "collect and supplement technical stack information (when necessary use web_search to search related technical choices and best practices)" in SKILL.md, which means it will fetch and interpret open/public web content that can materially influence architecture and tool decisions—exposing it to untrusted third‑party content that could enable indirect prompt injection.