sentry-triage

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

• Third-party content exposure detected (medium risk: 0.30). Sentry triage runtime uses the Sentry MCP toolchain (e.g., search_issues to pick an issue, then fetching specific issue/event context) and ingests attacker-controllable free text from Sentry event/issue fields (exception messages, breadcrumbs, tags, stack frames, request bodies) that are explicitly treated as untrusted.