ai-sdk

Warn

Audited by Snyk on Feb 21, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.70). The SKILL.md explicitly instructs the agent to fetch and read external documentation and live model listings (e.g., search ai-sdk.dev docs and run curl against https://ai-gateway.vercel.sh/v1/models) and to use those results to choose model IDs and drive code decisions, which means public third‑party content is ingested and can materially influence tool selection and behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 21, 2026, 04:23 PM