sentry-fix-issues

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly instructs the agent to fetch and analyze Sentry event data (e.g., get_issue_details, search_issue_events, get_event_attachment, and analyze_issue_with_seer) — all untrusted, user-controlled third-party content that the agent is expected to read and use to drive root-cause analysis and code fixes, so it could enable indirect prompt injection.