Security Review
doorkeeper-gem/doorkeeper
Verify that code changes do not introduce OAuth security vulnerabilities.
A skill your agent uses when reviewing security-sensitive code paths — check auth, secrets, input validation, dependency risk, and data exposure before shipping.
Install Project Security
$ npx skills add johnku2011/boilerplates-with-ai-skills --skill project-security -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install johnku2011/boilerplates-with-ai-skills project-security --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/johnku2011/boilerplates-with-ai-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/shared/skills/project-security .claude/skills/project-security && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "project-security" agent skill from https://github.com/johnku2011/boilerplates-with-ai-skills/tree/main/shared/skills/project-security into .claude/skills/project-security/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "project-security", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/johnku2011/boilerplates-with-ai-skills/tree/main/shared/skills/project-securityType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add johnku2011/boilerplates-with-ai-skills --skill project-security -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install johnku2011/boilerplates-with-ai-skills project-security --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/johnku2011/boilerplates-with-ai-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/shared/skills/project-security .agents/skills/project-security && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "project-security" agent skill from https://github.com/johnku2011/boilerplates-with-ai-skills/tree/main/shared/skills/project-security into .agents/skills/project-security/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "project-security", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add johnku2011/boilerplates-with-ai-skills --skill project-security -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install johnku2011/boilerplates-with-ai-skills project-security --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/johnku2011/boilerplates-with-ai-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/shared/skills/project-security .cursor/skills/project-security && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "project-security" agent skill from https://github.com/johnku2011/boilerplates-with-ai-skills/tree/main/shared/skills/project-security into .cursor/skills/project-security/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "project-security", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/johnku2011/boilerplates-with-ai-skills.git --path shared/skills/project-security--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add johnku2011/boilerplates-with-ai-skills --skill project-security -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install johnku2011/boilerplates-with-ai-skills project-security --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/johnku2011/boilerplates-with-ai-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/shared/skills/project-security .gemini/skills/project-security && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "project-security" agent skill from https://github.com/johnku2011/boilerplates-with-ai-skills/tree/main/shared/skills/project-security into .gemini/skills/project-security/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "project-security", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install johnku2011/boilerplates-with-ai-skills project-securityInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add johnku2011/boilerplates-with-ai-skills --skill project-security -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/johnku2011/boilerplates-with-ai-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/shared/skills/project-security .github/skills/project-security && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "project-security" agent skill from https://github.com/johnku2011/boilerplates-with-ai-skills/tree/main/shared/skills/project-security into .github/skills/project-security/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "project-security", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add johnku2011/boilerplates-with-ai-skills --skill project-security -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install johnku2011/boilerplates-with-ai-skills project-security --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/johnku2011/boilerplates-with-ai-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/shared/skills/project-security .opencode/skills/project-security && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "project-security" agent skill from https://github.com/johnku2011/boilerplates-with-ai-skills/tree/main/shared/skills/project-security into .opencode/skills/project-security/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "project-security", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
project-security- GitHub stars
- 240
- Token cost
- ~650 tokens
- SKILL.md length
- 270 words
- Files
- 2 (incl. references)
- Skills in repo
- 18
- Repo updated
- First seen
- Licence
- MIT
At a glance
A skill your agent uses when reviewing security-sensitive code paths — check auth, secrets, input validation, dependency risk, and data exposure before shipping.
- Works in 7 steps: Map trust boundaries — user input,… → Authentication & authorization — every… → Secrets — no keys/tokens in source,… → …
- Reviewing security-sensitive code paths — check auth
- SKILL.md covers Overview, When to Use, Process and Stack-Specific Checks, plus 4 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Project Security is an agent skill from johnku2011/boilerplates-with-ai-skills. Use when reviewing security-sensitive code paths — check auth, secrets, input validation, dependency risk, and data exposure before shipping.
Its SKILL.md is about 650 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/stack-checks.md`). Compatibility notes: Application source under review
It sits in Backend & APIs. The licence is MIT.
When your agent uses it
- Reviewing security-sensitive code paths — check auth
- Input validation
- Dependency risk
- Data exposure before shipping
Example prompts
- “/project-security”
Requirements
- Compatibility (from SKILL.md): Application source under review
- Pre-approved tools (allowed-tools): Read, Grep
Workflow steps
7 steps, taken from the first numbered list in SKILL.md.
- Map trust boundaries — user input, network, filesystem, subprocesses,
- Authentication & authorization — every new route/action must declare who
- Secrets — no keys/tokens in source, logs, client bundles, or error
- Input validation — validate query, body, headers, filenames, and IDs;
- Output encoding — prevent injection (HTML, SQL, shell, template).
- Dependencies — prefer existing libs; note new supply-chain surface.
- Data exposure — server-only data must not reach client, logs, or analytics.
What it can do on your machine
Read from SKILL.md and the folder at commit 475dc6a. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves these tools, so the agent can use them without asking each time:
ReadGrep
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Compatibility
Application source under review
From compatibility in the SKILL.md frontmatter.
Context cost
Project Security loads about 650 tokens when it runs, and up to ~802 if it reads all its reference files. Until then it costs about 40 tokens; SKILL.md has 270 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from johnku2011/boilerplates-with-ai-skills at commit 475dc6a, republished under its MIT licence (© johnku2011). 270 words, ~650 tokens.
Download SKILL.mdSave it as
.claude/skills/project-security/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- project-security
- description
- Use when reviewing security-sensitive code paths — check auth, secrets, input validation, dependency risk, and data exposure before shipping.
- allowed-tools
- Read, Grep
- compatibility
- Application source under review
- license
- MIT
- metadata.suite
- security
Project Security
Overview
Apply a practical security review to changes in this project. Focus on real exploitable issues, not generic checklists.
Core principle: Assume all external input is hostile. Assume secrets will leak unless kept server-side.
When to Use
- New or changed HTTP routes, API handlers, or auth flows
- File upload, subprocess, or shell execution
- Environment variable or config changes
- Dependency additions or version bumps
- Anything touching user data, tokens, or payments
Process
- Map trust boundaries — user input, network, filesystem, subprocesses, third-party APIs, client vs server.
- Authentication & authorization — every new route/action must declare who can call it and what they can access.
- Secrets — no keys/tokens in source, logs, client bundles, or error responses; env vars on server only.
- Input validation — validate query, body, headers, filenames, and IDs; reject early with safe error messages.
- Output encoding — prevent injection (HTML, SQL, shell, template).
- Dependencies — prefer existing libs; note new supply-chain surface.
- Data exposure — server-only data must not reach client, logs, or analytics.
Stack-Specific Checks
When the stack matters, read references/stack-checks.md
for web/API and mobile notes (progressive disclosure — load only if needed).
Severity Guide
| Severity | Examples |
|---|---|
| Blocking | Missing auth on privileged route, SQL/command injection, secret in client |
| High | Weak session handling, verbose errors leaking internals |
| Medium | Missing rate limit, overly broad CORS |
| Low | Defense-in-depth hardening, logging improvements |
Output Format
## Blocking
- [scenario] Issue — exploit path — fix
## Hardening
- Non-blocking improvements
## Verdict
safe to ship | ship with fixes | do not shipAnti-patterns
- Rubber-stamping without checking auth on new endpoints.
- Ignoring client-visible env vars or API responses that expose internals.
- Security theater (extra complexity without reduced risk).
- "We will add auth later" on production-bound code.
After Fixes
Re-check the diff. Run bwai scan-project if skills or agent config changed.
© johnku2011, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file (references) in shared/skills/project-security of johnku2011/boilerplates-with-ai-skills.
- SKILL.md
- references/stack-checks.md
Open the folder on GitHubat commit 475dc6a
Compare with similar skills
Project Security next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Project Security this skilljohnku2011/boilerplates-with-ai-skills | 240 | — | ~650 | Automated safety check: Pass | MIT | |
| Security Reviewdoorkeeper-gem/doorkeeper | 5.5k | — | ~1.4k | Automated safety check: Pass | MIT | |
| Ton Vulnerability Scannertrailofbits/skills | 7.4k | — | ~3.8k | Automated safety check: Pass | CC-BY-SA-4.0 | |
| Sast JWTutkusen/sast-skills | 1.3k | — | ~6k | Automated safety check: Pass | MIT | |
| Implementing Device Posture Assessment In Zero Trustmukul975/Anthropic-Cybersecurity-Skills | 34k | — | ~4.1k | Automated safety check: Pass | Apache-2.0 | |
| Audit Reconccashwell/evm-cortex | 131 | — | ~1.5k | Automated safety check: Pass | MIT |
Similar skills
- Official
Ton Vulnerability Scanner
trailofbits/skills
Scans TON (The Open Network) smart contracts for 3 critical vulnerabilities including integer-as-boolean misuse, fake Jetton contracts, and forward TON without gas checks.
Sast JWT
utkusen/sast-skills
Detect insecure JWT (JSON Web Token) implementations in a codebase using a two-phase approach: first map all JWT issuance and verification sites to understand the token lifecycle and signing…
Implementing Device Posture Assessment In Zero Trust
mukul975/Anthropic-Cybersecurity-Skills
Implements device posture assessment as a zero trust access control by integrating endpoint health signals from CrowdStrike ZTA, Microsoft Intune, and Jamf into conditional access policies that…
Audit Recon
ccashwell/evm-cortex
A skill your agent uses when performing initial audit reconnaissance.
Hunt Auth Bypass
sickn33/agentic-awesome-skills
Hunting skill for auth bypass vulnerabilities. An agent skill from sickn33/agentic-awesome-skills.
More from johnku2011/boilerplates-with-ai-skills
All 18 skills in this repoCode Review
johnku2011/boilerplates-with-ai-skills
A skill your agent uses when reviewing a diff or pull request — check correctness, tests, readability, security, and server/client boundaries before approving.
Python API Design
johnku2011/boilerplates-with-ai-skills
A skill your agent uses when adding or changing FastAPI routes, dependencies, or tests in this Python service — keep endpoints typed, validated, and covered by pytest.
Bwai Advisor
johnku2011/boilerplates-with-ai-skills
Use before scaffolding a bwai project — runs the full startup-goal workflow then recommends the right boilerplate and outputs the exact bwai new command to run.
Deploy Vercel
johnku2011/boilerplates-with-ai-skills
A skill your agent uses when deploying or configuring this project on Vercel — env vars, build settings, serverless limits, and production checks for Next.js or Express.
Express API Design
johnku2011/boilerplates-with-ai-skills
A skill your agent uses when adding or changing routes, middleware, or error handling in this Express.js API, to keep endpoints consistent, validated, and testable.
Nextjs App Router
johnku2011/boilerplates-with-ai-skills
A skill your agent uses when adding pages, layouts, route handlers, or data fetching in this Next.js App Router project, to follow server-first conventions correctly.
Related
Categories
Questions about Project Security
What does Project Security do?
A skill your agent uses when reviewing security-sensitive code paths — check auth, secrets, input validation, dependency risk, and data exposure before shipping. Project Security is an agent skill from johnku2011/boilerplates-with-ai-skills. Use when reviewing security-sensitive code paths — check auth, secrets, input validation, dependency risk, and data exposure before shipping.
When should I use Project Security?
Project Security fits situations like: reviewing security-sensitive code paths — check auth; input validation; dependency risk; data exposure before shipping.
How do I install Project Security in Claude Code?
Run `npx skills add johnku2011/boilerplates-with-ai-skills --skill project-security -a claude-code`. Or copy the skill folder (shared/skills/project-security in johnku2011/boilerplates-with-ai-skills) into .claude/skills/project-security in your project. Claude Code loads it when a task matches its description.
How do I install Project Security in Codex?
Run `npx skills add johnku2011/boilerplates-with-ai-skills --skill project-security -a codex`. Or copy the skill folder (shared/skills/project-security in johnku2011/boilerplates-with-ai-skills) into .agents/skills/project-security in your project. Codex loads it when a task matches its description.
Can I use Project Security in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add johnku2011/boilerplates-with-ai-skills --skill project-security -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/project-security, .gemini/skills/project-security, .github/skills/project-security and .opencode/skills/project-security in your project.
What does Project Security need to run?
SKILL.md names no scripts, command-line tools or credentials: Project Security is instructions for the agent only. Its frontmatter pre-approves these tools: Read, Grep. Compatibility (from SKILL.md): Application source under review.
Does Project Security access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Project Security safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Project Security use?
Project Security is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Project Security use?
About 650 tokens (SKILL.md is roughly 2.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 152 tokens, read only when the agent opens those files.
What are the alternatives to Project Security?
Skills that share tags, products or a category with Project Security: Security Review (doorkeeper-gem/doorkeeper, 5.5k stars), Ton Vulnerability Scanner (trailofbits/skills, 7.4k stars), Sast JWT (utkusen/sast-skills, 1.3k stars) and Implementing Device Posture Assessment In Zero Trust (mukul975/Anthropic-Cybersecurity-Skills, 34k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Project Security?
johnku2011 (a GitHub user) maintains it in johnku2011/boilerplates-with-ai-skills, which has 240 GitHub stars. The repository holds 18 skills in this directory. The repository was last updated on August 24, 2026.
Source: johnku2011/boilerplates-with-ai-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.