cqrs-architecture
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 mandatory step to "Verify patterns via MCP servers (perplexity, context7)" instructs the agent to consult external public MCP servers (e.g., Perplexity) as part of its workflow, which exposes it to untrusted third‑party content that could carry indirect prompt injection.
Audit Metadata