skills/openhands/extensions/vercel/Gen Agent Trust Hub

vercel

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill documents the use of standard Vercel CLI commands such as vercel login, vercel ls, and vercel logs. These are legitimate tools for developers managing cloud infrastructure.
  • [EXTERNAL_DOWNLOADS]: Includes instructions for vercel env pull, which allows users to synchronize environment variables from Vercel's official servers to their local environment. This is a standard feature of the Vercel platform.
  • [PROMPT_INJECTION]: Contains an <IMPORTANT> instructional block. This section provides benign guidance for the AI agent on how to assist users with Vercel's 'Deployment Protection' feature and does not attempt to override safety constraints or core instructions.
  • [DATA_EXFILTRATION]: Provides a mechanism for handling 'Protection Bypass' secrets. The instructions guide the user to provide these secrets to the agent to facilitate legitimate access to protected preview URLs, with no evidence of unauthorized data transmission to third-party domains.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 06:31 PM