deploy-to-vercel

Pass

Audited by Gen Agent Trust Hub on Aug 10, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Installs the official Vercel CLI via npm install -g vercel.
  • [DATA_EXFILTRATION]: Uploads project files to Vercel deployment endpoints (claude-skills-deploy.vercel.com and codex-deploy-skills.vercel.sh) as part of the intended deployment flow.
  • [COMMAND_EXECUTION]: Uses git, vercel, tar, and curl to prepare and execute project deployments.
  • [PROMPT_INJECTION]: Processes external project data (package.json) to detect frameworks, presenting a low risk of indirect prompt injection. 1. Ingestion points: package.json and project directory. 2. Boundary markers: None. 3. Capability inventory: curl, git, vercel, tar. 4. Sanitization: Excludes .env and .git files.
  • [SAFE]: The skill incorporates safety measures to prevent the accidental upload of secrets and sensitive metadata.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 10, 2026, 09:29 AM
Security Audit — agent-trust-hub — deploy-to-vercel