vulk — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited vulk (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Use VULK when the user asks to build, remix, inspect, edit, or deploy a website or web app from chat.
Prefer generate_immersive_site for briefs that mention:
Use create_project for general web projects.
Use get_project_files without includeContent first. Request file content only when needed, and request specific paths. Do not request secrets, .env files, credentials, private keys, certificates, .npmrc, .pypirc, .netrc, or service-account files.
Return the VULK project ID, preview URL, editor URL, and deployment URL when available. Do not describe VULK as a raw image, video, or audio generation API; VULK delivers editable web projects.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.