subagent-development
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 "External Technology Validation" and Known Issues sections explicitly require querying public third-party sources (e.g., microsoft-learn, perplexity, MCP servers, context7 and GitHub issues) and instruct the agent to read/validate information from those public sites, exposing it to untrusted web content that could enable indirect prompt injection.
Audit Metadata