sentry

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

• Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md and app.py show tools like get_issue_details, get_event_attachment, search_issue_events, and analyze_issue_with_seer that fetch and parse Sentry issue text, events, and attachments (user-generated/untrusted content from Sentry URLs), and that content is explicitly read and used to drive analysis and follow-up actions, creating an avenue for indirect prompt injection.