vibeteam-readiness

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

• Third-party content exposure detected (medium risk: 0.65). The skill’s runtime workflow uses curl to fetch health endpoints and other API responses (e.g., Sentry unresolved issues, Langfuse traces, GitHub issue title) and then pipes the returned JSON into jq, which becomes readable text in the agent’s context; these responses are outsider-authored content from third-party/public services.