sentry-triage-to-pr

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

• Third-party content exposure detected (high risk: 0.85). Outsider Sentry-authored free text is ingested at runtime via the operator’s capture/add_context path: it runs sentry issue list/view/events/explain/plan and sentry trace logs/replay view, parses the returned JSON, and then the agent later uses that bundle content to render GitHub issue bodies and subspawn prompts.