security-audit-static — Claude Code command: code security scanning
security-audit-static — a command to scan code for security vulnerabilities. Analyzes files, folders, or commit ranges and flags risks introduced by AI or manual changes.
MIT ★ 28,211 updated 2026-10-16
/plugin marketplace add phuryn/pm-skills
/plugin install pm-ai-shipping@pm-skillsWhat security-audit-static does
The command detects common security issues: injection vulnerabilities, exposed keys, unsafe cryptographic functions, hardcoded credentials, and other risks. It works on file paths, directories, commit ranges, or specific changes; by default it scans the entire repository.
Maintained in the ai-shipping plugin within phuryn/product-engineering by author Paweł Huryn. The copy here in pm-skills points to where it lives. If the plugin is already installed, use ai-shipping:security-audit-static instead — the local version will not load alongside it.
To use it, install the ai-shipping plugin from Claude Code's marketplace, then disable pm-ai-shipping in your local commands to avoid duplication.
What it helps with
- detect injection and data leak vulnerabilities
- identify unsafe cryptographic functions
- find hardcoded credentials and API keys
- audit code changes between commits for security issues
- review AI-generated code before deployment
Example prompts for the agent
- Check the security of
src/auth.js - Find vulnerabilities in changes between
mainandfeature-branch - Scan the
backend/directory for security problems
How to install security-audit-static
1Plugin marketplace
/plugin marketplace add phuryn/pm-skills/plugin install pm-ai-shipping@pm-skills2Manually: put the files in place
.claude/commands/security-audit-static.mdCall it with /security-audit-static. For all projects use ~/.claude/commands/
Manually: put the files in place
~/.codex/prompts/security-audit-static.mdCall it with /prompts:security-audit-static. Codex marks this format deprecated in favour of skills
Manually: put the files in place
.github/prompts/security-audit-static.prompt.mdManually: put the files in place
.gemini/commands/security-audit-static.tomlGemini stores commands as TOML: the prompt text goes into the prompt field
Questions about security-audit-static
How do I install security-audit-static in Claude Code?
Run /plugin marketplace add phuryn/pm-skills in Claude Code, then /plugin install pm-ai-shipping@pm-skills. After installation, the /security-audit-static command will be available.
What does security-audit-static check for?
It detects common vulnerabilities: injection attacks, exposed keys, unsafe cryptography, hardcoded passwords, and similar security issues.
Where is this command maintained now?
In the ai-shipping plugin at phuryn/product-engineering. If it's installed, use ai-shipping:security-audit-static instead of this copy.
Source text
security-audit-static.md · MIT
--- description: Moved to phuryn/product-engineering, where it is maintained in the ai-shipping plugin; this copy says where it went and how to install it. Use when asked to audit AI-built code for security risks. argument-hint: "<path or area> | <base>..<head> | changes; defaults to the whole repository" --- # /security-audit-static has moved `security-audit-static` is maintained in [phuryn/product-engineering](https://github.com/phuryn/product-engineering/tree/main/ai-shipping/skills/security-audit-static), in its `ai-shipping` plugin, with the rest of the AI Shipping Kit. This command, now a skill there, stays in pm-skills only so an agent that loads it knows where it went. - **`ai-shipping:security-audit-static` is installed:** use it, not this copy. - **It isn't:** tell the user that `security-audit-static` moved and how to install it, then help with the task as you would without it: ```bash claude plugin marketplace add phuryn/product-engineering claude plugin install ai-shipping@product-engineering ``` Other agents: [the repository's README](https://github.com/phuryn/product-engineering#install). Once it's installed, turn off `pm-ai-shipping` here, so this copy no longer loads beside it.
© Paweł Huryn · MIT · phuryn/pm-skills