Works with the AI tools you already use
Dependency vulnerability auditor
Audits project dependencies for CVEs, license compliance risks, and supply-chain attacks.
Free
See it in action
You say
I am adding 'lodahs' to my package.json for a commercial web app. Can you check if this is safe? Here is the file: {"dependencies": {"lodahs": "^4.17.21"}}
Your agent does
WARNING: 'lodahs' is a known typosquatting pattern for the popular 'lodash' library. This is a high-risk supply-chain red flag. Additionally, without a lockfile, the exact version resolved is non-deterministic. Recommendation: Remove 'lodahs' and install the official 'lodash' package instead.
About this skill
The problem
Dependency audits usually return a wall of version numbers without actual risk context. Developers often miss legal landmines like copyleft licenses or supply-chain red flags that haven't triggered a CVE yet.
What it does
- Analyzes
package.json,requirements.txt,Gemfile, andgo.modfiles for security gaps. - Identifies license contamination risks, specifically flagging AGPL/GPL dependencies in commercial projects.
- Detects supply-chain red flags such as typosquatting patterns and suspicious
postinstallscripts. - Prioritizes vulnerabilities based on reachability and fix availability rather than just severity scores.
Frameworks & tools
Supports Node.js (npm, yarn, pnpm), Python (pip, poetry), Ruby (Bundler), and Go. Integrates with osv-scanner, npm audit, and pip-audit output.
Why this beats prompting it yourself
General LLMs often hallucinate CVE numbers or provide outdated vulnerability data. This skill follows a strict protocol to use authoritative local tools and focuses on structural risks, like license shifts and mutable git dependencies, that basic prompts overlook.
Use cases
- Reviewing a pull request that adds new, unfamiliar third-party packages.
- Performing a license compliance sweep before a commercial product release.
- Investigating suspicious package behavior or potential typosquatting.
- Hardening supply-chain security by moving from branch-based to SHA-based pins.
Known limitations
Cannot perform live registry lookups. Analysis accuracy is significantly lower if a lockfile is not provided alongside the manifest.
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
Free forever
No account required to browse
Trust & safety
Security scanned
Verified clean today
- Free to download with an account