diagnostics-report-analyzer-skill

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

• Third-party content exposure detected (high risk: 0.75). The required workflow ingests the report’s embedded <script id="diagnostics-report-data" type="application/json">...</script> (outsider-authored HTML attachment content) and parses/feeds its agentHints/log messages into the LLM context, creating an indirect prompt-injection channel via producer-provided text.