sentry-debug-issue

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

• Third-party content exposure detected (medium risk: 0.30). The runtime workflow uses Sentry MCP tools like get_sentry_resource / search_issues to read attacker-controlled exception messages, breadcrumbs, request bodies, tags, user context, and stack frames from Sentry issues/events at debug time, so outsider-authored free text embedded in those fields is ingested for the agent to reason over.