report-writing

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow explicitly instructs the agent to fetch and check public third‑party sources—e.g., querying the HackerOne directory (curl "https://hackerone.com/directory"), reading repository SECURITY.md or GitHub profile via gh api, and inspecting package registries (npm/pip)—and to use those external, user‑authored results to decide disclosure channel, so untrusted web content will be read and can influence subsequent actions.