Cybersecurity Skills for AI Agents

A collection of cybersecurity skills for AI coding agents. The AI does the heavy lifting; you bring the context about your stack and your priorities.

Built to be useful at every experience level:

• Security engineers and pentesters running formal audits — concrete grep patterns, OWASP / NIST / ATT&CK alignment, report templates that pass auditor review
• Developers shipping safer code without a dedicated security team to lean on — security work that fits into a normal sprint, plain-English explanations of why each finding matters
• Founders, ops folks, and small-team operators securing a stack they can’t afford a CISO for — guided, opinionated playbooks for the most common security work, with the audit skill explaining what it found and why
• Red / blue / purple teams running real engagements — offensive recon, web pentest, threat hunting, detection engineering, SOC operations

You do not need to be a security expert to use these skills. The skills are written so the AI agent can run them end-to-end and explain the findings in language any technical reader can follow. If you can describe what you have and what you want to know about it, the agent can do the work.

Skills are authored as Claude Code SKILL.md files (the canonical format) and built into adapters for Cursor and Codex. Installable via npx skills or the Claude Code plugin marketplace.

Built by Bri Russell. I run real audits with these skills, then bring the gaps I find back into the skill itself — so each version is a little less opinion and a little more evidence.

Contributions welcome! Field feedback is the most valuable contribution — whether you’re a security engineer who hit a gap during an audit, a developer whose AI agent missed something obvious, or a founder who used a skill and got an answer that wasn’t quite right. Open a PR or open an issue — every level of expertise produces useful signal.

Where to start

Not every skill is for every user on day one. A good starting point by context:

• Not sure? Ask for security-start (or just say “where do I start with security?”). It asks two or three questions and picks the skill.
• Reviewing your own code or product: start with owasp-audit for the source-code sweep, then api-audit if you have API endpoints, then dependency-audit for the CVE pass
• A CVE wave just dropped and you run many apps: patch-sweep to work out which apps are affected and ship fixes across the fleet, with dependency-audit for each project
• Want deterministic scanners in CI instead of asking an agent to “hack” your app: scanner-pipeline picks the tools per layer, wires them into CI, and routes findings to finding-triage
• Securing cloud / infrastructure: start with cloud-audit (AWS / GCP / Azure misconfig), then iam-audit if you manage identities, then container-audit if you run Docker / Kubernetes
• Responding to “something happened”: incident-triage for the immediate response, disk-forensics if you need to analyze a system afterward, malware-triage for a suspicious file someone found, security-comms to draft the stakeholder / customer communications
• No SIEM, no security staff, but you have logs: log-watch sets up a scheduled agent that reads the logs you already have (Vercel, Heroku, Sentry, Supabase, Stripe, CloudTrail, GitHub) and pages someone when it matters
• You are the security team (founder / solo operator): personal-opsec audits your own accounts, devices and AI-agent setup first — the person holding the keys is usually the softest target
• Building a security program from scratch: csf-mapping for the governance frame, threat-modeling before new features, breach-patterns to learn from public incidents
• Working under a specific regulation: privacy-engineering for GDPR / CCPA / similar privacy laws, hipaa-audit for ePHI, pci-audit for payment cards, control-audit for SOC 2, ISO 27001 or FedRAMP audit readiness, ai-risk-management for AI features
• Running AI coding agents with skills, plugins, or MCP servers: agent-supply-chain-audit before you install or trust them — including this catalog
• Closing the loop on findings: finding-triage for any single finding from any source — gives you a defensible disposition with the right ticket fields
• Translating security work upward or outward: security-comms for board / exec / customer / engineering / sales-engineering deliverables

The offensive skills (recon, osint-recon, web-pentest, red-team-engagement) require explicit authorization for the target and assume more security context. They open with an authorization check and will refuse anything ambiguous. red-team-engagement in particular carries the strongest refusal posture in the catalog and will refuse to plan anything against systems the user cannot demonstrate authorization for.

What are Skills?

Skills are markdown files that give AI agents specialized knowledge and workflows for specific tasks. Drop them into your project and your agent recognizes when you’re working on a security task and applies the right methodology — OWASP categories, NIST IR steps, MITRE ATT&CK references, the actual grep patterns that surface the bug.

The goal isn’t to replace a security engineer — or to pretend you have one if you don’t. It’s to give the agent enough structure that the first pass is useful, the report format is consistent, and the obvious stuff stops slipping through. For teams without dedicated security headcount, that closes a real gap. For teams with security engineers, it lets them spend their time on the work the AI can’t do.

How Skills Work Together

The skills are organized into seven families. Most security work crosses families — an OWASP audit surfaces a dependency question, an incident kicks off an OSINT trail, cloud findings overlap with appsec, and findings have to be translated for the audience that hears them. Skills cross-reference each other where that’s true; finding-triage, security-comms, and csf-mapping orchestrate across the whole map.

             ┌──────────────────────────────────────────┐
             │         Cybersecurity Skill Map          │
             └─────────────────────┬────────────────────┘
                                   │
   ┌─────────┬──────────┬──────────┼─────────┬──────────┬───────────┐
   ▼         ▼          ▼          ▼         ▼          ▼           ▼
┌──────┐ ┌────────┐ ┌────────┐ ┌────────┐ ┌──────┐ ┌─────────┐ ┌──────────┐
│AppSec│ │Offens. │ │Detect &│ │Cloud & │ │ AI   │ │Design & │ │Complianc │
│& Sup │ │& Recon │ │Respond │ │ Infra  │ │Secur.│ │Governnce│ │& Privacy │
├──────┤ ├────────┤ ├────────┤ ├────────┤ ├──────┤ ├─────────┤ ├──────────┤
│owasp-│ │recon   │ │incid-  │ │cloud-  │ │promp-│ │threat-  │ │privacy-  │
│ audit│ │osint-  │ │ triage │ │ audit  │ │ inj. │ │ modeling│ │ engineer-│
│api-  │ │ recon  │ │disk-   │ │contain-│ │ai-   │ │vuln-    │ │ ing      │
│ audit│ │web-    │ │ forens.│ │ audit  │ │ risk-│ │ research│ │pci-audit │
│depen-│ │ pentest│ │siem-   │ │iam-aud-│ │ mgmt │ │finding- │ │hipaa-    │
│ audit│ │red-    │ │ detect.│ │ it     │ │agent-│ │ triage  │ │ audit    │
│secre-│ │ team-  │ │soc-    │ │        │ │supply│ │csf-     │ │control-  │
│ audit│ │ engage-│ │ ops    │ │        │ │-chain│ │ mapping │ │ audit    │
│crypt-│ │ ment   │ │threat- │ │        │ │-audit│ │security-│ │          │
│ audit│ │business│ │ hunting│ │        │ │      │ │ comms   │ │          │
│mobile│ │-logic- │ │breach- │ │        │ │      │ │personal-│ │          │
│-audit│ │-testing│ │patterns│ │        │ │      │ │ opsec   │ │          │
│patch-│ │        │ │log-    │ │        │ │      │ │security-│ │          │
│ sweep│ │        │ │ watch  │ │        │ │      │ │ start   │ │          │
│scan- │ │        │ │malware-│ │        │ │      │ │         │ │          │
│ner-  │ │        │ │ triage │ │        │ │      │ │         │ │          │
│pipe- │ │        │ │        │ │        │ │      │ │         │ │          │
│line  │ │        │ │        │ │        │ │      │ │         │ │          │
│cicd- │ │        │ │        │ │        │ │      │ │         │ │          │
│ sec. │ │        │ │        │ │        │ │      │ │         │ │          │
│vari- │ │        │ │        │ │        │ │      │ │         │ │          │
│ ant- │ │        │ │        │ │        │ │      │ │         │ │          │
│ anal.│ │        │ │        │ │        │ │      │ │         │ │          │
│native│ │        │ │        │ │        │ │      │ │         │ │          │
│-code-│ │        │ │        │ │        │ │      │ │         │ │          │
│review│ │        │ │        │ │        │ │      │ │         │ │          │
│fuzz- │ │        │ │        │ │        │ │      │ │         │ │          │
│ing-  │ │        │ │        │ │        │ │      │ │         │ │          │
│ harn.│ │        │ │        │ │        │ │      │ │         │ │          │
└──┬───┘ └───┬────┘ └───┬────┘ └───┬────┘ └──┬───┘ └────┬────┘ └────┬─────┘
   │         │          │          │         │          │           │
   └─────────┴──────────┴──────────┼─────────┴──────────┴───────────┘
                                   │
   Common crossovers:
     owasp-audit ↔ api-audit ↔ dependency-audit ↔ vuln-research
     web-pentest ↔ recon ↔ osint-recon ↔ red-team-engagement
     siem-detection → threat-hunting → incident-triage → disk-forensics
     cloud-audit ↔ container-audit ↔ iam-audit ↔ secrets-audit
     threat-modeling → owasp-audit / api-audit (pre-implementation → code)
     prompt-injection ⇆ ai-risk-management (security slice ⇆ whole lifecycle)
     privacy-engineering ⇆ hipaa-audit / pci-audit (engineering ⇆ regulatory)
     agent-supply-chain-audit ⇆ dependency-audit / secrets-audit (agent extensions are supply chain too)
     owasp-audit (source-side race patterns) → business-logic-testing (prove it live) ← web-pentest
     dependency-audit (one project) → patch-sweep (the whole fleet)
     scanner-pipeline → finding-triage → fix agents (tools find it, agents fix it)
     log-watch → siem-detection / soc-operations (outgrow it) → incident-triage (it's real)
     personal-opsec → iam-audit / secrets-audit / agent-supply-chain-audit (the person → the org → the agents)
     dependency-audit → cicd-security ← agent-supply-chain-audit (the pipeline is supply chain too)
     dependency-audit → cicd-security ← agent-supply-chain-audit (the pipeline is supply chain too)
     finding-triage → variant-analysis → scanner-pipeline (one bug → a rule → it can't come back)
     native-code-review ↔ crypto-audit (memory safety ↔ constant time and key handling)
     native-code-review ↔ fuzzing-harness (read the parser ↔ fuzz it)
     incident-triage → malware-triage → siem-detection / threat-hunting (the sample → detections and hunts)
     control-audit ⇆ csf-mapping / pci-audit / hipaa-audit (audit readiness ⇆ framework mapping)
     security-start → any skill (a vague ask → the right first step)
     breach-patterns → every audit skill (what to check)
     finding-triage ← every audit skill (closes the loop on any finding)
     security-comms ← every skill (translates output for non-security audience)
     csf-mapping ← every skill (rolls evidence into governance frame)

Available Skills

Want to see the output first? examples/ has real runs of five audit skills against a small vulnerable app.

Every offensive skill enforces an authorization check before doing anything; every skill refuses destructive or unauthorized use. Details in Ethics & Authorization.

Installation

Option 1: npx skills (recommended)

The vercel-labs/skills installer reads the canonical skills/ directory directly:

# List available skills
npx skills add briiirussell/cybersecurity-skills --list

# Install all skills
npx skills add briiirussell/cybersecurity-skills

# Install specific skills
npx skills add briiirussell/cybersecurity-skills --skill owasp-audit api-audit

Installs to your .agents/skills/ directory with a symlink into .claude/skills/ for Claude Code compatibility.

Option 2: Claude Code plugin marketplace

/plugin install cybersecurity-skills --marketplace briiirussell/cybersecurity-skills

That’s one step on Claude Code 2.1.275 or later. On older versions, add the marketplace first:

/plugin marketplace add briiirussell/cybersecurity-skills
/plugin install cybersecurity-skills

The plugin also ships one subagent, finding-verifier. Audit skills hand it one candidate finding at a time, and it tries to disprove the finding in a fresh, read-only context. Cursor and Codex don’t get the subagent; they follow the same steps from verification.md.

Option 3: Claude Code (project-level, manual)

git clone https://github.com/briiirussell/cybersecurity-skills.git
cp -r cybersecurity-skills/skills/owasp-audit .claude/skills/

Trigger naturally (“run an OWASP audit on this codebase”) or invoke directly with /owasp-audit.

Option 4: Claude Code (personal, all projects)

cp -r cybersecurity-skills/skills/owasp-audit ~/.claude/skills/

Option 5: Cursor

cp adapters/cursor/owasp-audit.mdc .cursor/rules/

Option 6: Codex

cp adapters/codex/owasp-audit.md /

Option 7: Git submodule (easy updates)

git submodule add https://github.com/briiirussell/cybersecurity-skills.git .agents/cybersecurity-skills

Then reference skills from .agents/cybersecurity-skills/skills/.

Building Adapters

After creating or modifying a skill, regenerate the Cursor + Codex adapters:

node scripts/build-adapters.mjs   # adapters + shared reference copies
node scripts/lint-skills.mjs      # frontmatter, size, cross-reference and link lint
npm test                          # findings / coverage validators, SARIF export, build (Node ≥ 21, no dependencies)

Files in shared/ (the findings.json schema and validator, severity calibration, verification and coverage guides) are copied into each skill’s references/ folder according to shared/manifest.json, because npx skills installs one skill folder at a time. Edit shared/, never the copies.

Creating a New Skill

1. Copy templates/skill-template.md to skills//SKILL.md
2. Fill in the frontmatter (name, description, allowed-tools)
3. Write instructions in imperative form, under 500 lines
4. Add trigger prompts in evals/triggers/.json (see evals/README.md)
5. Run the build script to generate adapters, then npm run check

Format details and writing guidance live in CLAUDE.md. Full contribution flow in CONTRIBUTING.md.

Security scanning

Every PR is linted and scanned with NVIDIA SkillSpector (static mode, pinned version). Intentional example payloads — a security skill has to name ~/.aws/credentials and show what an injection looks like — are suppressed by narrow, reasoned rules in .skillspector-baseline.yaml. Scan it yourself before installing:

skillspector scan https://github.com/briiirussell/cybersecurity-skills --recursive --no-llm

Our baseline is never applied to your scan; SkillSpector only uses an author-shipped baseline for a single skill with --use-shipped-baseline. allowed-tools lists tools pre-approved to run without a prompt in Claude Code — it is not a sandbox — and the Cursor / Codex adapters carry no tool restrictions at all. Details: docs/security-scanning.md. You can also point agent-supply-chain-audit at this repo.

Found a way a skill could lead an agent to do something unsafe, like an over-broad grant or an instruction that skips the authorization check? Please report it privately. SECURITY.md has what’s in scope and how.

Ethics & Authorization

These skills are for authorized security testing, CTF competitions, security research, and defensive use only. Every offensive skill (recon, osint-recon, web-pentest, etc.) opens with an authorization check and refuses destructive techniques, mass targeting, supply-chain compromise, or evasion patterns intended for malicious use.

If you’re using these against a system you don’t own or have explicit written authorization to test, you are using them wrong. Don’t.

Versioning

This repo follows semantic versioning. See VERSIONS.md for the full changelog and GitHub Releases for release notes.

• MAJOR (X.0.0) — Breaking changes: skill renames, removals, or frontmatter changes that break existing installs
• MINOR (1.X.0) — New skill, or substantive expansion of an existing one
• PATCH (1.0.X) — Content fixes, grep-pattern updates, small additions

Every new skill and every skill improvement ships as its own version, one PR each, so each skill’s version in VERSIONS.md tells you exactly what changed and when.

Contributing

See CONTRIBUTING.md. The short version: field feedback (PRs or issues with concrete patterns from a real audit) is the highest-signal contribution. If a skill missed something in your audit, that’s exactly what I want to know. Open a field report. If one found something real, I’d love a trophy case entry.

License

MIT — see LICENSE.