sentry-fix-stack-traces

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

• Third-party content exposure detected (medium risk: 0.30). The skill reads “a real event” at runtime via MCP (search_issues then get_sentry_resource) and explicitly treats the returned event fields (frame paths, exception text, breadcrumbs, tags) as attacker-controlled free text, creating indirect prompt-injection exposure.