sentry-fix-issues

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly ingests Sentry event data via MCP tools (e.g., get_issue_details, search_issue_events, get_event_attachment, analyze_issue_with_seer) — SKILL.md even labels exception messages, breadcrumbs, request bodies and attachments as "untrusted external input" that the agent must read and use to drive root-cause analysis and fixes, which could allow indirect prompt-injection.