sentry-fix-stack-traces

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 instructs the agent to “Pull the event — via the MCP (search_issues, then get_sentry_resource) or the issue URL the user gives you” and then “Read the frames themselves” and classify MCP-returned frame paths/exception text/tags as attacker-controllable.