Skip to content

About

Claude skill that audits dependencies against OSV.dev for malicious and vulnerable packages — detects Shai-Hulud, s1ngularity, supply-chain attacks, and CVEs across 8 ecosystems

Resources

Stars

0 stars

Watchers

0 watching

Forks

Latest commit

 

History

1 Commit

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 

Repository files navigation

compromised-package-checker

A Claude skill that audits your project's dependencies against OSV.dev — Google's open vulnerability database — and flags compromised, malicious, or vulnerable package versions before they reach production.

What it does

  1. Walks your project directory and finds all dependency files
  2. Parses them into (package, version, ecosystem) triples — lockfiles preferred over manifests
  3. Batch-queries OSV.dev for known issues
  4. Reports findings in two buckets:
    • Malicious / compromised — remove or roll back (supply-chain attacks, worms, exfiltrators)
    • Vulnerable — upgrade to the fixed version (regular CVEs)

Ecosystems supported

Ecosystem Files parsed
npm package-lock.json, yarn.lock, pnpm-lock.yaml, package.json
PyPI poetry.lock, Pipfile.lock, uv.lock, requirements.txt, pyproject.toml
Cargo Cargo.lock
Go go.sum
RubyGems Gemfile.lock
Composer composer.lock
Maven pom.xml
NuGet *.csproj, packages.lock.json

Usage

As a Claude skill

Install compromised-package-checker.skill through Claude's skill settings, then ask:

  • "Check my project for compromised packages"
  • "Audit my dependencies"
  • "Am I affected by Shai-Hulud?"
  • "Scan my lockfile for malicious packages"

Directly from the command line

# Full audit
python3 scripts/check.py /path/to/your/project

# Malicious packages only
python3 scripts/check.py /path/to/your/project --malicious-only

# JSON output (for CI pipelines)
python3 scripts/check.py /path/to/your/project --json

No external dependencies — pure Python stdlib. PyYAML is optional (improves YAML parsing).

In CI (GitHub Actions)

- name: Audit dependencies
  run: |
    python3 scripts/check.py . --json > audit.json
    python3 -c "
    import json, sys
    d = json.load(open('audit.json'))
    mal = d['totals']['malicious']
    crit = sum(1 for f in d['findings'] if f['severity'] == 'CRITICAL')
    sys.exit(1 if mal or crit else 0)
    "

Exit codes

Code Meaning
0 Clean — no findings
1 Findings present
2 Error (no lockfiles found, parse failure)

Data source

All vulnerability data comes from OSV.dev — a free, read-only, key-free API that aggregates:

  • GitHub Advisory Database (GHSA)
  • PyPA, RustSec, Go vuln DB
  • npm audit feed
  • OSSF Malicious Packages Repository (MAL-* IDs)

A clean scan means "nothing known today." Zero-days and fresh compromises may take hours to appear in OSV.

Notable attacks it detects

  • Shai-Hulud — self-replicating npm worm (Sept 2025, 500+ packages)
  • s1ngularity — credential exfiltrator across PyPI and npm
  • chalk/debug compromise — phishing-driven maintainer takeover
  • Any package with an active MAL-* OSV advisory

License

MIT

About

Claude skill that audits dependencies against OSV.dev for malicious and vulnerable packages — detects Shai-Hulud, s1ngularity, supply-chain attacks, and CVEs across 8 ecosystems

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages