sentry-debug-issue

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

• Third-party content exposure detected (medium risk: 0.30). SKILL.md’s Step 1–2 drives the agent to read Sentry issue/event context via MCP tools like get_sentry_resource (and to locate issues via search_issues natural-language queries), meaning attacker-controlled text from outsider-authored Sentry issue/event contents is ingested at runtime.