axiom-analyze-triage

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

• Third-party content exposure detected (high risk: 0.85). The required workflow fetches outsider-authored free text from Sentry/App Store Connect at runtime (e.g., Sentry issue/event bodies and frames via GET /api/0/issues/{id}/events/latest/ and ASC diagnostic logs via metrics_get_diagnostic_logs), which is then normalized into JSONL and fed into xcsym triage/the agent’s LLM context.