Vercel CLI

Pass

Audited by Gen Agent Trust Hub on Aug 30, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructions include the installation of the 'vercel' CLI via the npm registry. This is an expected dependency for a tool originating from a well-known service.
  • [COMMAND_EXECUTION]: The skill leverages shell commands to execute Vercel CLI operations, including deployment, project synchronization, and environment variable manipulation.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection where untrusted data could influence agent behavior.
  • Ingestion points: The agent reads deployment logs and project metadata through the vercel logs and vercel inspect commands defined in SKILL.md.
  • Boundary markers: There are no explicit delimiters or instructions to ignore potential commands embedded in logs or project data.
  • Capability inventory: The skill provides capabilities to write sensitive environment variables (vercel env add) and trigger production deployments (vercel deploy --prod) as described in SKILL.md.
  • Sanitization: There is no evidence of filtering or sanitizing the content retrieved from Vercel logs or deployment inspections.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 30, 2026, 12:31 AM
Security Audit — agent-trust-hub — Vercel CLI