Updated 1d ago
by Srajangpt1
ai-security-crew
Security for AI coding agents, covering the code they write and the actions they take. MCP server, skills and a runtime guard.
72 GitHub stars (72)
- 3 skills (3 skills found in its SKILL.md files)
- 26 forks (26 forks)
- 1d ago last update (Last updated 1d ago)
Install
Skills CLI
npx skills add Srajangpt1/ai-security-crew
Asks which skills and agents to install. Just one: npx skills add Srajangpt1/ai-security-crew --skill security-review — add -g for every project.
Claude Code
git clone https://github.com/Srajangpt1/ai-security-crewcp -r "ai-security-crew/skills/security-review" ~/.claude/skills/
Copies the security-review skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add Srajangpt1/ai-security-crew
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md.
-
security-review
Pre-coding security review for a development task: which parts of the system it touches, the threats to guard against, and the countermeasures to build in. Use before coding a feature, or when the user asks about security requirements, risks, or how to build something safely (login, payments, file upload, APIs, agents, MCP servers, and so on).
skills/security-review/SKILL.md on GitHub (opens in a new tab) -
threat-model
Developer-focused threat model for a feature, component or system: what can go wrong, how likely, and the concrete fix for each threat, with an optional threat-model.md file. Use when the user asks to threat model something, what attacks to worry about, the attack surface, a security design review, or is designing a feature involving auth, payments, file handling, multi-tenancy, external APIs, ag…
skills/threat-model/SKILL.md on GitHub (opens in a new tab) -
verify-code
Security review of code that was just written or changed. Use after generating code, or when the user asks whether code is secure, to check for vulnerabilities, or to audit a file before shipping (especially auth, APIs, file handling, database queries, agents or anything that handles user input).
skills/verify-code/SKILL.md on GitHub (opens in a new tab)
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.
Similar skills
-
superpowersby obra An agentic skills framework & software development methodology that works.
-
skillsby mattpocock Skills for Real Engineers. Straight from my .agents directory.
-
reaby morluto Reverse engineer anything with agents, from app behavior down to native binaries.
-
ECCby affaan-m The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Cod…
-
andrej-karpathy-skillsby multica-ai A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
-
skillsby anthropics Public repository for Agent Skills