Deepsec Documentation Guide
vercel-labs/deepsec
Points the agent at deepsec's own docs to answer questions about initializing, configuring, resuming, scanning with and extending the vulnerability scanner.
Harden an application or service against common attack vectors.
Install Security Hardening
$ npx skills add agulli/atlas-agents --skill security-hardening -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install agulli/atlas-agents security-hardening --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/agulli/atlas-agents.git skills-src && mkdir -p .claude/skills && cp -r skills-src/ch09_agent_skills/skills/security-hardening .claude/skills/security-hardening && 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 "security-hardening" agent skill from https://github.com/agulli/atlas-agents/tree/main/ch09_agent_skills/skills/security-hardening into .claude/skills/security-hardening/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "security-hardening", 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/agulli/atlas-agents/tree/main/ch09_agent_skills/skills/security-hardeningType 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 agulli/atlas-agents --skill security-hardening -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install agulli/atlas-agents security-hardening --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agulli/atlas-agents.git skills-src && mkdir -p .agents/skills && cp -r skills-src/ch09_agent_skills/skills/security-hardening .agents/skills/security-hardening && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "security-hardening" agent skill from https://github.com/agulli/atlas-agents/tree/main/ch09_agent_skills/skills/security-hardening into .agents/skills/security-hardening/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "security-hardening", 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 agulli/atlas-agents --skill security-hardening -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install agulli/atlas-agents security-hardening --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agulli/atlas-agents.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/ch09_agent_skills/skills/security-hardening .cursor/skills/security-hardening && 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 "security-hardening" agent skill from https://github.com/agulli/atlas-agents/tree/main/ch09_agent_skills/skills/security-hardening into .cursor/skills/security-hardening/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "security-hardening", 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/agulli/atlas-agents.git --path ch09_agent_skills/skills/security-hardening--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 agulli/atlas-agents --skill security-hardening -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install agulli/atlas-agents security-hardening --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agulli/atlas-agents.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/ch09_agent_skills/skills/security-hardening .gemini/skills/security-hardening && 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 "security-hardening" agent skill from https://github.com/agulli/atlas-agents/tree/main/ch09_agent_skills/skills/security-hardening into .gemini/skills/security-hardening/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "security-hardening", 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 agulli/atlas-agents security-hardeningInstalls 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 agulli/atlas-agents --skill security-hardening -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/agulli/atlas-agents.git skills-src && mkdir -p .github/skills && cp -r skills-src/ch09_agent_skills/skills/security-hardening .github/skills/security-hardening && 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 "security-hardening" agent skill from https://github.com/agulli/atlas-agents/tree/main/ch09_agent_skills/skills/security-hardening into .github/skills/security-hardening/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "security-hardening", 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 agulli/atlas-agents --skill security-hardening -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install agulli/atlas-agents security-hardening --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agulli/atlas-agents.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/ch09_agent_skills/skills/security-hardening .opencode/skills/security-hardening && 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 "security-hardening" agent skill from https://github.com/agulli/atlas-agents/tree/main/ch09_agent_skills/skills/security-hardening into .opencode/skills/security-hardening/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "security-hardening", 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
security-hardening- GitHub stars
- 579
- Token cost
- ~714 tokens
- SKILL.md length
- 321 words
- Files
- 1
- Skills in repo
- 12
- Repo updated
- First seen
- Licence
- MIT
At a glance
Harden an application or service against common attack vectors.
- Works in 3 steps: Verify all endpoints require… → Check that authorization is enforced at… → Confirm tokens expire. JWTs must have…
- Asked to improve security posture
- SKILL.md covers Overview, Process, Rationalizations and Verification
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Security Hardening is an agent skill from agulli/atlas-agents. Harden an application or service against common attack vectors. Use when asked to improve security posture, secure an API, harden a server, or prepare for a security review.
Its SKILL.md is about 710 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Security, covering Security review. The licence is MIT.
When your agent uses it
- Asked to improve security posture
- Harden a server
- Prepare for a security review
Example prompts
- “/security-hardening”
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
- Verify all endpoints require authentication. Check for unprotected routes using
- Check that authorization is enforced at the data layer, not just the route layer. A user who can reach /orders should only see their orders.
- Confirm tokens expire. JWTs must have exp claims. Sessions must have server-side expiry.
What it can do on your machine
Read from SKILL.md and the folder at commit 2b21998. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).
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.
Context cost
Security Hardening loads about 714 tokens when it runs. Until then it costs about 48 tokens; SKILL.md has 321 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: notes
The automated check noted patterns worth knowing about, such as sudo or a known installer.
- NoteMentions a .env fileSKILL.md:37
8. Check `.gitignore` includes `.env`, `*.key`, `*.pem`.
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 agulli/atlas-agents at commit 2b21998, republished under its MIT licence (© agulli). 321 words, ~714 tokens.
Download SKILL.mdSave it as
.claude/skills/security-hardening/SKILL.md (or your agent's skills folder).- name
- security-hardening
- description
- Harden an application or service against common attack vectors. Use when asked to improve security posture, secure an API, harden a server, or prepare for a security review.
- license
- MIT
Overview
Security hardening is not about chasing perfect — it's about raising the cost of attack above the attacker's budget. Work systematically through the layers.
Process
Layer 1: Authentication and Authorization
- Verify all endpoints require authentication. Check for unprotected routes using:
bash grep -rn "route\|@app\.\|router\." src/ | grep -v "login\|health\|docs" - Check that authorization is enforced at the data layer, not just the route layer. A user who can reach
/ordersshould only see their orders. - Confirm tokens expire. JWTs must have
expclaims. Sessions must have server-side expiry.
Layer 2: Input Validation
- Every user-supplied value that touches a database must use parameterized queries. Grep for f-string SQL:
bash grep -rn "f\"SELECT\|f'SELECT\|format.*SELECT" src/ - Every file path from user input must be validated against an allowlist or a sandboxed directory. Check for
os.path.join(base, user_input)withoutos.path.abspath+startswithguard.
Layer 3: Secrets and Configuration
- Scan for hardcoded secrets:
bash grep -rn "password\s*=\s*[\"'][^\"']\|api_key\s*=\s*[\"'][^\"']" src/ - Confirm all secrets come from environment variables or a secrets manager, not from config files committed to version control.
- Check
.gitignoreincludes.env,*.key,*.pem.
Layer 4: Dependencies and Infrastructure
- Run the
dependency-auditskill to check for vulnerable packages. - Check HTTP security headers are set (for web services):
Content-Security-PolicyX-Frame-Options: DENYStrict-Transport-SecurityX-Content-Type-Options: nosniff
Layer 5: Output
- Write findings as a prioritized list: Critical → High → Medium → Low. For each finding: what it is, where it is (file:line), how to fix it.
Rationalizations
| Excuse | Rebuttal |
|---|---|
| "This is an internal service, it doesn't need hardening" | Internal services are the primary target of lateral movement attacks after initial breach. |
| "We'll harden it before the public launch" | Security debt compounds. Fix it before it goes anywhere. |
| "The framework handles security" | Frameworks handle some things. You must handle the application-level concerns. |
Verification
- All four layers were checked (not just the ones that seemed relevant)
- No hardcoded secrets found in source or git history
- Every critical and high finding has a specific remediation
- A finding was produced for each layer — even if it's "no issues found"
© agulli, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in ch09_agent_skills/skills/security-hardening of agulli/atlas-agents.
Open the folder on GitHubat commit 2b21998
Compare with similar skills
Security Hardening 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 |
|---|---|---|---|---|---|---|
| Security Hardening this skillagulli/atlas-agents | 579 | — | ~714 | Automated safety check: Notes | MIT | |
| Deepsec Documentation Guidevercel-labs/deepsec | 8.1k | — | ~956 | Automated safety check: Pass | Apache-2.0 | |
| Kubernetes Network Security Auditkubeshark/kubeshark | 12k | — | ~7.3k | Automated safety check: Notes | Apache-2.0 | |
| Native Dependency Updatemono/SkiaSharp | 5.6k | — | ~4.1k | Automated safety check: Pass | MIT | |
| Semgrep Security Scantrailofbits/skills | 7.4k | — | ~3.7k | Automated safety check: Notes | CC-BY-SA-4.0 | |
| Skillward AuditFangcun-AI/SkillWard | 143 | — | ~2.9k | Automated safety check: Pass | Custom licence |
Similar skills
- Official
Kubernetes Network Security Audit
kubeshark/kubeshark
Hunts for compromised workloads and malicious traffic in a Kubernetes cluster by sweeping network data through Kubeshark MCP, mapped to MITRE ATT&CK.
Native Dependency Update
mono/SkiaSharp
Update native dependencies (libpng, libexpat, zlib, libwebp, harfbuzz, freetype, libjpeg-turbo, etc.) in SkiaSharp's Skia fork.
- Official
Semgrep Security Scan
trailofbits/skills
Detects languages, proposes rulesets for approval, then runs the approved Semgrep scan across a codebase and merges the output into one SARIF file.
Skillward Audit
Fangcun-AI/SkillWard
Security-audit a third-party skill bundle (folder with SKILL.md, or .zip / .tar.gz archive) before installing it, using the SkillWard cloud scanner.
Security Audit
TheDecipherist/claude-code-mastery
Checks a codebase for hardcoded secrets, vulnerable dependencies, weak input handling, weak authentication and unsafe transport settings before deployment or merge.
More from agulli/atlas-agents
All 12 skills in this repoAPI Design
agulli/atlas-agents
Design or review REST and GraphQL API interfaces. An agent skill from agulli/atlas-agents.
Data Pipeline
agulli/atlas-agents
Design, build, or debug data processing pipelines. An agent skill from agulli/atlas-agents.
Database Migration
agulli/atlas-agents
Safely run database schema migrations. An agent skill from agulli/atlas-agents.
Deploy Checklist
agulli/atlas-agents
Execute a structured deployment to staging or production. An agent skill from agulli/atlas-agents.
Documentation Writer
agulli/atlas-agents
Write or update technical documentation for code, APIs, or systems.
Git Commit
agulli/atlas-agents
Create well-structured git commits with conventional commit messages.
Related
Categories
Questions about Security Hardening
What does Security Hardening do?
Harden an application or service against common attack vectors. Security Hardening is an agent skill from agulli/atlas-agents. Harden an application or service against common attack vectors.
When should I use Security Hardening?
Security Hardening fits situations like: asked to improve security posture; harden a server; prepare for a security review.
How do I install Security Hardening in Claude Code?
Run `npx skills add agulli/atlas-agents --skill security-hardening -a claude-code`. Or copy the skill folder (ch09_agent_skills/skills/security-hardening in agulli/atlas-agents) into .claude/skills/security-hardening in your project. Claude Code loads it when a task matches its description.
How do I install Security Hardening in Codex?
Run `npx skills add agulli/atlas-agents --skill security-hardening -a codex`. Or copy the skill folder (ch09_agent_skills/skills/security-hardening in agulli/atlas-agents) into .agents/skills/security-hardening in your project. Codex loads it when a task matches its description.
Can I use Security Hardening 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 agulli/atlas-agents --skill security-hardening -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/security-hardening, .gemini/skills/security-hardening, .github/skills/security-hardening and .opencode/skills/security-hardening in your project.
What does Security Hardening need to run?
SKILL.md names no scripts, command-line tools or credentials: Security Hardening is instructions for the agent only.
Does Security Hardening 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 Security Hardening safe to install?
Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
What licence does Security Hardening use?
Security Hardening 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 Security Hardening use?
About 714 tokens (SKILL.md is roughly 2.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Security Hardening?
Skills that share tags, products or a category with Security Hardening: Deepsec Documentation Guide (vercel-labs/deepsec, 8.1k stars), Kubernetes Network Security Audit (kubeshark/kubeshark, 12k stars), Native Dependency Update (mono/SkiaSharp, 5.6k stars) and Semgrep Security Scan (trailofbits/skills, 7.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Security Hardening?
agulli (a GitHub user) maintains it in agulli/atlas-agents, which has 579 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on July 17, 2026.
Source: agulli/atlas-agents on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.