website-publisher

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill documentation describes using shell execution to invoke command-line tools for site deployment, including Netlify CLI, Vercel CLI, and Wrangler (Cloudflare). These operations are the primary intended function of the skill for publishing static sites.
  • [EXTERNAL_DOWNLOADS]: The skill references well-known technology services for hosting, such as Vercel, Netlify, and Cloudflare Pages. These are recognized as safe, well-known services.
  • [PROMPT_INJECTION]: The blog post drafting functionality ingests untrusted project artifacts and user-provided 'authorAngle' text to generate content. This represents an indirect prompt injection surface, but is constrained to the skill's primary purpose of drafting posts from provided data.
  • [SAFE]: The skill follows security best practices by reading deployment tokens from environment variables rather than storing them in local configuration files.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 03:12 PM
Security Audit — agent-trust-hub — website-publisher