next-upgrade
Warn
Audited by Snyk on Mar 3, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly instructs the agent to "Use WebFetch" to retrieve official Next.js upgrade guides from nextjs.org (e.g., https://nextjs.org/docs/app/guides/upgrading/codemods and version-specific upgrade pages), which the agent must read and use to determine migration steps and run codemods, so third-party web content can directly influence its actions.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill instructs running remote code at runtime via the codemod command "npx @next/codemod@latest ", which fetches and executes an external npm package and is presented as a required step for the upgrade.
Audit Metadata