Skip to main content
skill CX Codex

sca-audit — Claude Code skill: what it does, how to install

sca-audit scans project dependencies for known CVEs, highlights abandoned packages, and suggests exact remediation commands.

CC-BY-4.0 358 installs ★ 230 updated 2026-10-15

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add OWASP/secure-agent-playbook --skill sca-audit -a claude-code
Open on GitHub

What sca-audit does

The skill guides an agent through Software Composition Analysis across lockfiles and package manifests. It covers Node.js, Python, Go, Java, Ruby, Rust, .NET, and PHP projects by running existing CLI scanners like osv-scanner, npm audit, pip-audit, govulncheck, or trivy.

Without at least one vulnerability scanner installed on your machine, the skill halts and asks you to install one (such as osv-scanner), because manual CVE inspection across dozens of indirect packages is prone to errors. When reporting findings, it checks whether vulnerable methods are reachable, flags packages inactive for over two years, and catches typosquatting or licensing issues.

The final output includes a breakdown by severity using a structured finding template, quick overview tables, and exact shell commands to patch each flaw.

What it helps with

  • audit project manifests and lockfiles for published CVEs
  • triage alerts coming from Dependabot or Renovate
  • verify reachability of vulnerable code paths before updating
  • flag inactive dependencies untouched for two or more years

Example prompts for the agent

  • Run an SCA audit on all lockfiles in this repo
  • Triage Dependabot vulnerability alerts for our requirements.txt
  • Scan package-lock.json with osv-scanner and list remediation steps

How to install sca-audit

1Skills CLI (Vercel)

npx skills add OWASP/secure-agent-playbook --skill sca-audit -a claude-code

2Manually: put the files in place

~/.claude/skills/sca-audit/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/sca-audit/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about sca-audit

How to install sca-audit in Claude Code?

Run npx skills add OWASP/secure-agent-playbook --skill sca-audit -a claude-code in your terminal.

What does the sca-audit skill do?

It coordinates dependency auditing by locating manifests, executing scanners like osv-scanner or npm audit, and evaluating exploitability context alongside dependency health.

What tools must be installed before running this audit?

You need a local scanner such as osv-scanner, trivy, npm audit, pip-audit, or govulncheck. If none are detected, the skill prompts you to install one.

Source text

SKILL.md · CC-BY-4.0
---
name: sca-audit
description: Scan project dependencies for known vulnerabilities (CVEs). Use when reviewing dependency files (package.json, requirements.txt, go.mod, pom.xml, Gemfile, Cargo.toml, etc.), triaging Dependabot/Renovate alerts, or performing pre-deployment security checks.
license: CC-BY-4.0
---

# Software Composition Analysis Audit

Scan dependencies for known CVEs by following the full procedure in `plays/sca-audit.md`.

## Steps

1. **Identify Dependency Manifests** — Scan for all dependency files and lockfiles across ecosystems (Node.js, Python, Go, Java, Ruby, Rust, .NET, PHP). Prefer lockfiles for exact resolved versions.

2. **Run Vulnerability Scan** — Use available tools in preference order:
   - `osv-scanner --lockfile=<path> --format=json` (recommended, multi-ecosystem)
   - `npm audit --json` (Node.js)
   - `pip-audit -r requirements.txt --format=json` (Python)
   - `govulncheck ./...` (Go)
   - `trivy fs --format json --scanners vuln <path>` (multi-ecosystem)
   - If no scanner is installed, **stop and ask the user to install one** (e.g., `brew install osv-scanner`). Manual analysis is not viable — even small projects have 50+ dependencies. For individual package triage, point the user to [OSV.dev](https://osv.dev/list).

3. **Analyze Results** — For each vulnerability: determine reachability (is the vulnerable code path used?), check exploitability context (deployment matters), and identify fix availability (patch vs major version bump).

4. **Dependency Health** — Beyond CVEs, flag unmaintained packages (2+ years inactive), typosquatting risks, license concerns, and version pinning issues.

## Output

Scan summary (ecosystems, dependency count, scanner used), findings sorted by severity using `templates/finding.md`, condensed table for medium/low, dependency health flags, and exact remediation commands.

## OWASP References

- A06:2021: Vulnerable and Outdated Components
- OWASP Dependency-Check
- OWASP SCVS

© OWASP · CC-BY-4.0 · OWASP/secure-agent-playbook

Similar skills

All skills for Security →

From the same set18

The whole set →
api-security-review The api-security-review skill runs an API through the OWASP API Security Top 10 (2023), covering auth, BOLA, SSRF and gateway config. Useful before a release or when auditing someone else's service. CX Codex +1 684installs code-review-security code-review-security — a skill that reviews code for vulnerabilities against OWASP Top 10 and ASVS, then reports findings with attack scenarios and fixed snippets. CX Codex +1 516installs security-guidance The security-guidance skill applies OWASP ASVS guidance to code involving input, auth, storage, networks, files, cryptography, or access control. CX Codex +1 492installs secrets-scan secrets-scan scans source and config files for hardcoded credentials, API keys and tokens, whether you are reviewing before a merge or auditing a repo. CX Codex +1 427installs agent-security-audit agent-security-audit is a Claude Code skill that checks AI agent configurations for vulnerabilities. Run it when reviewing CLAUDE.md files, MCP configs, and agent orchestration code. CX Codex +1 302installs mobile-code-review mobile-code-review audits native Android and iOS source code for security vulnerabilities against the OWASP MASVS v2.1.0 benchmark. CX Codex +1 224installs prompt-injection-test prompt-injection-test runs an LLM app through prompt injection attacks from the Arcanum PI Taxonomy. Use it when red-teaming your own AI app or checking how well its guardrails hold. CX Codex +1 220installs mcp-server-review mcp-server-review is a Claude Code skill that audits MCP server code and client settings for security risks. Run it to review a server or assess it before installation. CX Codex +1 217installs

Project sponsors

Companies that keep this analytics open