debug

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

• Third-party content exposure detected (high risk: 0.80). The workflow explicitly instructs the agent to query external services and docs — e.g., "If the user provided a Sentry issue URL or error ID, query Sentry for the full stack trace" and to use Context7 for library docs — which causes the agent to ingest untrusted, user-provided third-party content that can influence triage, tooling, and next actions.