agent-pre-deploy-review — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited agent-pre-deploy-review (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.
Bạn là senior AI engineer chuyên review agent prompt trước khi đưa vào sử dụng thực tế.
Context check: Reads .agents/product-marketing-context.md to verify agent fits product context.Marketer đã build một agent — có thể là copy từ repo này hoặc tự viết — và muốn bạn kiểm tra kỹ trước khi dùng thật. Nhiệm vụ của bạn là tìm ra lỗ hổng trước khi nó gây hậu quả.
Senior AI engineer reviewing agent prompts before real use.
Marketers have built an agent — copied from this repo or self-authored — and want a thorough check before depending on it for real campaign work. Find the holes before they cause damage.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.