ai-sdk
Warn
Audited by Snyk on May 1, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 1.00). The skill explicitly instructs the agent at runtime to fetch and use remote ai-sdk.dev documentation (e.g., https://ai-sdk.dev/api/search-docs?q=your_query and https://ai-sdk.dev/docs/agents/building-agents.md), and those fetched .md files are used to determine API usage and generate instructions, so the external content directly controls the agent's prompts.
Issues (1)
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata