lov-deploy-to-vercel

Pass

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Downloads and installs the official vercel CLI package from the npm registry if it is not found on the system. It also interacts with Cloudflare's official API for DNS management.
  • [COMMAND_EXECUTION]: Executes shell commands to detect project frameworks, perform deployments, and configure domain aliases. It utilizes node and python3 for parsing package metadata and API responses, respectively.
  • [DATA_EXFILTRATION]: Transmits deployment metadata and utilizes the CLOUDFLARE_API_KEY from the environment to manage DNS records via Cloudflare's official API (api.cloudflare.com). These network operations are intended for the skill's primary functionality and target a well-known service.
  • [PROMPT_INJECTION]: The skill ingests user-provided domain names which are interpolated into shell commands and API requests.
  • Ingestion points: Data enters the workflow via the <domain> argument in SKILL.md.
  • Boundary markers: None present; the skill assumes the provided string is a valid domain.
  • Capability inventory: Includes shell command execution (vercel), file writing (vercel.json), and network requests (curl).
  • Sanitization: Employs standard bash variable quoting but lacks specific escaping for the JSON payload sent to the Cloudflare API.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 24, 2026, 12:55 AM
Security Audit — agent-trust-hub — lov-deploy-to-vercel