Works with the AI tools you already use
Dependency & Supply Chain Risk Gate
Audit your project's dependencies for supply-chain risk before they ship. Detects the ecosystem, runs the right vulnerability scanners against live advisory data, and adds the checks tooling misses — outdated or abandoned packages, typosquatted or suspicious names, risky install scripts, and license conflicts — then returns a prioritized fix list and a PASS / REVIEW / BLOCK verdict. It's npm audit with triage and judgment on top.
Secure checkout via Stripe
See it in action
You say
Audit the dependencies in this Node project — are we safe to ship?
Your agent does
A risk report: BLOCK on a high-severity prototype-pollution CVE in a transitive lodash version (safe minor-bump fix, top of the fix list); REVIEW a direct dependency whose repo was archived three years ago (plan a replacement); and a flag that a package named "reqeusts" may be a typosquat of "requests" — worth verifying, not assumed malicious. Verdict: BLOCK until the lodash fix lands.
What you get
About this skill
Most of a project's risk isn't in code the team wrote — it's in the hundreds of transitive packages it pulled in: known CVEs, abandoned libraries, a typosquatted name one character off a popular package, an install script doing something it shouldn't, or a copyleft license in a proprietary product. This gate orchestrates the right tooling and adds the human-judgment layer scanners can't: • Detects the ecosystem and lockfiles (npm/pnpm/yarn, pip/Poetry, Go, Cargo, Bundler, Maven, and more) • Runs the appropriate scanner against live advisory data — never stale memory of CVEs • Triages by severity × reachability × fix availability, flagging breaking-change fixes • Flags outdated, deprecated, and abandoned packages • Surfaces supply-chain signals tooling misses — typosquatting, low-trust packages, risky install scripts, non-registry sources, ownership changes — flagged to verify, never accused • Checks license risk (informational, not legal advice) • Returns a prioritized fix list and a PASS / REVIEW / BLOCK verdict It catches the fixable critical that actually matters and tells you the one upgrade to make first — not a wall of raw audit output.
How to install
Drop the file into your AI Agent. Works with Claude, Cursor, ChatGPT, and 20+ more.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill passes our trust checks below.
Security scanned
Passed our 8-point scan before listing
Fresh listing
Recently published to Agensi
30-day refund
Not a fit? Get your money back
Trust & safety
Security scanned
Verified clean 1 month ago
- 30-day refund guarantee
- One-time purchase, yours forever
- Secure checkout via Stripe
Creator
PubsProToolkit builds rigor-first skills for AI agents — they write your docs and content properly, then adversarially review them to catch what's wrong before it ships. The result: cleaner output and a hard quality gate in one toolkit. Built by a CMPP-certified, PhD medical writer who brings regulated-industry standards to developer docs, content, compliance, and research integrity.
Also available in a bundle
Frequently Asked Questions
Popular in Security & Compliance
Bounty Security Pattern Master Library — 399 Vulnerability Patterns
A premium library of 399 vulnerability patterns and DeFi attack vectors for AI-driven bug hunting and security audits.

sast-configuration
Automate the setup and optimization of Semgrep, SonarQube, and CodeQL for high-signal security testing.
dependency-health-check
Automated security audit and health check for software dependencies across polyglot projects.
code-repair-spine
Generate source-safe repository audits and repair handoff bundles without mutating your code.