Works with the AI Agents you already use
Dependency vulnerability auditor
Audits project dependencies for CVEs, license compliance risks, and supply-chain attacks.
$1.99
Dependency vulnerability auditor
Example session with this skill installed
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"}}
- Read your context and instructions
- Compiled the dependency vulnerability auditor
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.
Connects securely to your tools. The creator never sees your data.
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General LLMs often hallucinate CVE numbers or provide outdated vulnerability data.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.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Security.
Requires a lockfile for precise version analysis. Cannot perform real-time network lookups to check the latest registry state.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 2 months ago