skills/udecode/plate/vercel-sandbox/Gen Agent Trust Hub

vercel-sandbox

Pass

Audited by Gen Agent Trust Hub on Mar 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSCREDENTIALS_UNSAFE
Full Analysis
  • [COMMAND_EXECUTION]: Executes administrative and application-level commands (dnf, npm, agent-browser) inside an isolated Vercel Sandbox VM to configure the browser environment.
  • [EXTERNAL_DOWNLOADS]: Fetches system libraries and the agent-browser package from official package registries (dnf and NPM) during the VM setup process.
  • [CREDENTIALS_UNSAFE]: Retrieves Vercel authentication tokens and project metadata from environment variables (VERCEL_TOKEN, VERCEL_TEAM_ID, VERCEL_PROJECT_ID) to authorize the creation and management of sandbox instances.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 15, 2026, 06:10 AM