sentry-setup-releases

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

• Third-party content exposure detected (medium risk: 0.30). [SKILL.md → Step 1 (diagnosis) instructs the agent to pull a “recent event via the MCP (search_issues, then get_sentry_resource)” and to treat MCP-returned fields (including messages/frame paths) as untrusted input; since issue/event text is outsider-authored, this is indirect prompt-injection exposure at runtime.]