sentry

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

• Third-party content exposure detected (high risk: 0.85). The skill’s required workflow uses the Sentry MCP tools (e.g., mcp__sentry__search_issues, mcp__sentry__search_events, mcp__sentry__search_issue_events) to fetch issue/event text from Sentry at runtime, which is outsider-authored content (Sentry project data created by other users/clients) that the agent then ingests into the LLM context.