monitor
Warn
Audited by Snyk on Feb 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill explicitly expects the agent to read and analyze untrusted, user-generated monitoring data—e.g., paste error messages and stack traces from Sentry dashboards and user-reported issues/logs from uptime/error-monitoring services like Sentry, UptimeRobot, and platform logs—so the agent would ingest third-party content that could contain indirect prompt injections.
Audit Metadata