84%
Total Score
healthy
Very active, well-backed project with strong packaging and provenance; workflow permissions and an untrusted checkout warrant caution.
The repository name does not match the package and its README does not mention @ai-sdk/mistral, creating a package-to-repository transparency gap; the Vercel organization and monorepo structure partly compensate for this.
All 13 workflows were analyzed and action references are pinned, but a workflow_run workflow performs an untrusted checkout and two workflows grant top-level write access; high-confidence blanket app permissions also need tightening. The cache-poisoning findings are low confidence and do not materially change the assessment.
We didn't find any vulnerabilities for this package.
| Dependency | Last Release | Score |
|---|---|---|
@ai-sdk/provider Version 4.0.28 | — | — |
@ai-sdk/provider-utils Version 5.0.61 | — | — |
Connect your repositories to instantly see whether vulnerable or malicious packages exist in your codebase.
Free. No credit card required.

I consent to receiving marketing communications based on Aikido’s Privacy Policy.
SOC 2Compliant
ISO 27001Compliant
ISO 42001Compliant© All Intel data is openly available and commercially licensed.