troubleshoot
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: 0.80). The skill's Step 1 Research explicitly instructs the agent to "WebSearch for error messages, known issues" and to spawn a research-specialist agent, which means it will fetch and read open/public web content (untrusted/user-generated) as part of its workflow.
Audit Metadata