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