Skip to content
Back to search

SecuritySkills

Open-source security skills for AI coding agents. Grounded in OWASP, NIST, MITRE ATT&CK, CIS. Works with Claude Code, Gemini CLI, Cursor, Codex CLI, OpenClaw, Kiro.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/unitoneai--securityskills/badge.svg)](/listings/unitoneai--securityskills)

HTML

<a href="/listings/unitoneai--securityskills"><img src="/api/listings/unitoneai--securityskills/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

git clone https://github.com/UnitOneAI/SecuritySkills.git
cd SecuritySkills

**Claude Code** (native format — auto-discovery and `/slash-commands`)

# Global install — all skills available via auto-discovery and /skill-name
cp -r skills/*/* ~/.claude/skills/

# Or project-local
mkdir -p .claude/skills && cp -r skills/*/* .claude/skills/

# Then use naturally:
# "Review this code for security issues"    → Claude auto-loads secure-code-review
# /threat-modeling                          → Direct invocation
# /cve-triage CVE-2024-1234                 → With arguments

**Gemini CLI**

# Reference skills via @ commands
cp -r skills/ ~/.gemini/skills/

**Cursor**

# Add as Cursor rules
cp -r skills/ .cursor/rules/

**Codex CLI / Kiro / Generic**

# Point any agent at a skill's SKILL.md file
codex --context skills/appsec/threat-modeling/SKILL.md "Review this design"
kiro spec --skill skills/ai-security/llm-top-10/SKILL.md

Each skill is a directory with `SKILL.md` as the entrypoint, following the [Agent Skills](https://agentskills.io) open standard. Claude Code discovers skills automatically; other tools can load them by path.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 331 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # Security Skills for AI Coding Agents
  2. **Drop structured security skills into your AI coding agent. Get instant, framework-grounded security expertise.**
  3. ![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)
  4. ![Skills: 45](https://img.shields.io/badge/Skills-45-green.svg)
  5. ![Claude Code](https://img.shields.io/badge/Claude_Code-compatible-purple.svg)
  6. ![Gemini CLI](https://img.shields.io/badge/Gemini_CLI-compatible-purple.svg)
  7. ![Cursor](https://img.shields.io/badge/Cursor-compatible-purple.svg)
  8. ![Codex CLI](https://img.shields.io/badge/Codex_CLI-compatible-purple.svg)
  9. ![OpenClaw](https://img.shields.io/badge/OpenClaw-compatible-purple.svg)
  10. ![Kiro](https://img.shields.io/badge/Kiro-compatible-purple.svg)
  11. ---
  12. ## Why This Exists
  13. AI coding agents can perform security reviews, but they hallucinate framework control numbers, miss entire vulnerability categories, and produce inconsistent output across runs. The result is security guidance that sounds authoritative but falls apart under scrutiny.
  14. These skills ground agents in real published frameworks -- OWASP, NIST, MITRE ATT&CK, and CIS Controls -- so that every finding maps to a verifiable control. They are not prompt dumps. They are structured, framework-referenced, injection-hardened skill files that produce reliable, auditable security output.
  15. ## Quick Start
  16. ```bash
  17. git clone https://github.com/UnitOneAI/SecuritySkills.git
  18. cd SecuritySkills
  19. ```
  20. **Claude Code** (native format — auto-discovery and `/slash-commands`)
  21. ```bash
  22. # Global install — all skills available via auto-discovery and /skill-name
  23. cp -r skills/*/* ~/.claude/skills/
  24. # Or project-local
  25. mkdir -p .claude/skills && cp -r skills/*/* .claude/skills/
  26. # Then use naturally:
  27. # "Review this code for security issues" → Claude auto-loads secure-code-review
  28. # /threat-modeling → Direct invocation
  29. # /cve-triage CVE-2024-1234 → With arguments
  30. ```
  31. **Gemini CLI**
  32. ```bash
  33. # Reference skills via @ commands
  34. cp -r skills/ ~/.gemini/skills/
  35. ```
  36. **Cursor**
  37. ```bash
  38. # Add as Cursor rules
  39. cp -r skills/ .cursor/rules/
  40. ```
  41. **Codex CLI / Kiro / Generic**
  42. ```bash
  43. # Point any agent at a skill's SKILL.md file
  44. codex --context skills/appsec/threat-modeling/SKILL.md "Review this design"
  45. kiro spec --skill skills/ai-security/llm-top-10/SKILL.md
  46. ```
  47. Each skill is a directory with `SKILL.md` as the entrypoint, following the [Agent Skills](https://agentskills.io) open standard. Claude Code discovers skills automatically; other tools can load them by path.
  48. ## Skill format
  49. Every skill is a **directory** at `skills/<domain>/<skill-name>/` with `SKILL.md` as the entrypoint, following the [Agent Skills](https://agentskills.io) open standard.
  50. ### `SKILL.md` frontmatter
  51. All skills use the same YAML frontmatter fields:
  52. ```yaml
  53. name: threat-modeling # kebab-case, matches the directory
  54. description: > # what it does + when it auto-invokes
  55. Runs a structured STRIDE threat model on any design, API spec, or codebase...
  56. tags: [appsec, design, architecture] # domain + activity keywords
  57. role: [security-engineer, architect] # which role bundles include it
  58. phase: [design, review] # SDLC phase
  59. frameworks: [STRIDE, MITRE-ATT&CK] # cited frameworks — real control IDs only
  60. difficulty: intermediate # beginner | intermediate | advanced
  61. time_estimate: "30-60min"
  62. version: "1.0.0"
  63. author: unitoneai
  64. license: MIT
  65. allowed-tools: Read, Grep, Glob # tools the skill may use
  66. injection-hardened: true # reviewed against OWASP LLM01
  67. argument-hint: "[target-file-or-directory]"
  68. # context: fork # optional
  69. ```
  70. The machine-readable schema for this frontmatter lives at
  71. [`schemas/skill.schema.json`](schemas/skill.schema.json). Validate all skills
  72. and role bundles locally with:
  73. ```bash
  74. ruby scripts/validate_skill_schema.rb
  75. ```
  76. Validate skill fixture manifests and expected evidence strings with:
  77. ```bash
  78. ruby scripts/test_skill_fixtures.rb
  79. ```
  80. Validate remediation regression manifests and expected auto-fix diffs with:
  81. ```bash
  82. ruby scripts/test_remediation_fixtures.rb
  83. ```
  84. Regenerate the deterministic skill quality scorecard with:
  85. ```bash
  86. ruby scripts/generate_quality_scorecard.rb
  87. ruby scripts/generate_quality_scorecard.rb --check
  88. ```
  89. Validate framework provenance, versions, owners, and review dates with:
  90. ```bash
  91. ruby scripts/validate_framework_registry.rb
  92. ruby scripts/validate_framework_registry.rb --stale --max-age-days 365
  93. ```
  94. Validate required domain CODEOWNERS review gates with:
  95. ```bash
  96. ruby scripts/validate_codeowners.rb
  97. ```
  98. Release archives include SHA-256 checksums generated by the release workflow.
  99. See [`docs/release-integrity.md`](docs/release-integrity.md) for verification
  100. steps.
  101. CI/CD examples for GitHub Actions, GitLab CI, Azure DevOps, Jenkins,
  102. pre-commit, and local agent usage are available in
  103. [`docs/ci-cd-examples.md`](docs/ci-cd-examples.md). Validate those examples
  104. locally with:
  105. ```bash
  106. ruby scripts/validate_ci_cd_examples.rb
  107. ```
  108. ### Normalized finding JSON
  109. Every skill must be able to emit findings as normalized JSON that validates
  110. against [`schemas/finding.schema.json`](schemas/finding.schema.json). The
  111. top-level envelope, required run/skill metadata, finding fields, evidence,
  112. framework/CWE references, remediation fields, and test strategy requirements are
  113. documented in [`docs/normalized-json-output.md`](docs/normalized-json-output.md).
  114. When SARIF is requested, skills should map those normalized findings to
  115. SARIF 2.1.0-compatible JSON using [`docs/sarif-output.md`](docs/sarif-output.md).
  116. When tracker handoff is requested, skills should map normalized findings to
  117. tracker-ready work items using
  118. [`docs/tracker-handoff.md`](docs/tracker-handoff.md) and
  119. [`schemas/tracker-handoff.schema.json`](schemas/tracker-handoff.schema.json).
  120. ### Progressive disclosure (keep `SKILL.md` lean)
  121. Claude's skill guidance: when a `SKILL.md` would exceed ~500 lines, **don't inline everything** — split detail into sibling reference files in the same directory and link to them from `SKILL.md`. The agent loads a reference only when it needs it, so the entrypoint stays cheap to load.
  122. ```
  123. skills/appsec/threat-modeling/
  124. ├── SKILL.md ← entrypoint (lean): when-to-use, rules, output format
  125. ├── threat-actor-profiles.md ← reference, loaded on demand
  126. └── csharp-dotnet.md ← language-specific reference
  127. ```
  128. This is why some skills ship extra `.md` files alongside `SKILL.md` (e.g. `cloud/aws-review/benchmark-checklist.md`, `compliance/soc2-gap/tsc-criteria.md`) — it is the intended pattern, not duplication.
  129. ---
  130. ---
  131. ## Skills
  132. 45 skills across 10 security domains.
  133. ### Application Security
  134. | Skill | Path | Frameworks |
  135. |-------|------|------------|
  136. | Threat Modeling (STRIDE) | `skills/appsec/threat-modeling/` | STRIDE, PASTA, MITRE ATT&CK |
  137. | Secure Code Review | `skills/appsec/secure-code-review/` | OWASP ASVS 4.0.3, CWE Top 25 |
  138. | OWASP Top 10 (Web) | `skills/appsec/owasp-top-10-web/` | OWASP Top 10 2021 |
  139. | API Security Review | `skills/appsec/api-security/` | OWASP API Security Top 10 2023 |
  140. | Dependency Scanning | `skills/appsec/dependency-scanning/` | SLSA v1.0, CycloneDX, SPDX |
  141. ### AI Security
  142. | Skill | Path | Frameworks |
  143. |-------|------|------------|
  144. | LLM Top 10 Review | `skills/ai-security/llm-top-10/` | OWASP LLM Top 10 2025 |
  145. | Agentic AI Top 10 | `skills/ai-security/agentic-top-10/` | OWASP Agentic AI, MITRE ATLAS |
  146. | Prompt Injection Testing | `skills/ai-security/prompt-injection/` | OWASP LLM01:2025, MITRE ATLAS |
  147. | Model Supply Chain | `skills/ai-security/model-supply-chain/` | OWASP LLM03:2025, SLSA v1.0 |
  148. | AI Data Privacy | `skills/ai-security/ai-data-privacy/` | NIST AI RMF, OWASP LLM02:2025 |
  149. | Agent Security Architecture | `skills/ai-security/agent-security/` | OWASP Agentic AI, NIST AI RMF |
  150. ### Identity & Access
  151. | Skill | Path | Frameworks |
  152. |-------|------|------------|
  153. | IAM Security Review | `skills/identity/iam-review/` | NIST SP 800-63B, CIS Controls v8 |
  154. | Access Review | `skills/identity/access-review/` | CIS Controls v8, NIST SP 800-53 |
  155. | RBAC/ABAC Design | `skills/identity/rbac-design/` | NIST RBAC, NIST SP 800-162 |
  156. | Zero Trust Assessment | `skills/identity/zero-trust-assessment/` | NIST SP 800-207, CISA ZTMM v2 |
  157. | Privileged Access Management | `skills/identity/privileged-access/` | CIS Controls v8, NIST SP 800-53 |
  158. ### Cloud Security
  159. | Skill | Path | Frameworks |
  160. |-------|------|------------|
  161. | AWS Security Review | `skills/cloud/aws-review/` | CIS AWS Benchmark v3.0 |
  162. | Azure Security Review | `skills/cloud/azure-review/` | CIS Azure Benchmark v2.1 |
  163. | GCP Security Review | `skills/cloud/gcp-review/` | CIS GCP Benchmark v2.0 |
  164. | IaC Security | `skills/cloud/iac-security/` | OWASP IaC Security, SLSA v1.0 |
  165. | Container Security | `skills/cloud/container-security/` | CIS Docker v1.6, CIS K8s v1.9 |
  166. ### Vulnerability Management
  167. | Skill | Path | Frameworks |
  168. |-------|------|------------|
  169. | CVE Triage | `skills/vuln-management/cve-triage/` | CVSS 4.0, SSVC 2.1, CISA KEV, EPSS |
  170. | Patch Prioritization | `skills/vuln-management/patch-prioritization/` | SSVC 2.1, EPSS, CISA KEV |
  171. | SBOM Analysis | `skills/vuln-management/sbom-analysis/` | CycloneDX, SPDX, VEX |
  172. | Scanner Tuning | `skills/vuln-management/scanner-tuning/` | CVSS 4.0, CWE |
  173. ### Compliance
  174. | Skill | Path | Frameworks |
  175. |-------|------|------------|
  176. | SOC 2 Gap Analysis | `skills/compliance/soc2-gap/` | AICPA TSC |
  177. | ISO 27001 Gap Analysis | `skills/compliance/iso27001-gap/` | ISO 27001:2022 |
  178. | PCI DSS Review | `skills/compliance/pci-dss-review/` | PCI DSS v4.0 |
  179. | HIPAA Review | `skills/compliance/hipaa-review/` | HIPAA Security Rule |
  180. | NIST CSF Assessment | `skills/compliance/nist-csf-assessment/` | NIST CSF 2.0 |
  181. ### Incident Response
  182. | Skill | Path | Frameworks |
  183. |-------|------|------------|
  184. | IR Playbook | `skills/incident-response/ir-playbook/` | NIST SP 800-61 |
  185. | Forensics Checklist | `skills/incident-response/forensics-checklist/` | NIST SP 800-86, RFC 3227 |
  186. | Containment Strategies | `skills/incident-response/containment/` | NIST SP 800-61, MITRE ATT&CK |
  187. | Post-Incident Review | `skills/incident-response/post-incident-review/` | NIST SP 800-61 |
  188. ### SecOps
  189. | Skill | Path | Frameworks |
  190. |-------|------|------------|
  191. | Detection Engineering | `skills/secops/detection-engineering/` | MITRE ATT&CK v16, Sigma |
  192. | SIEM Rules | `skills/secops/siem-rules/` | MITRE ATT&CK v16 |
  193. | Alert Triage | `skills/secops/alert-triage/` | MITRE ATT&CK v16 |
  194. | Log Analysis | `skills/secops/log-analysis/` | MITRE ATT&CK v16, NIST SP 800-92 |
  195. ### Network Security
  196. | Skill | Path | Frameworks |
  197. |-------|------|------------|
  198. | Firewall Rule Audit | `skills/network/firewall-review/` | CIS Controls v8, NIST SP 800-41 |
  199. | Network Segmentation | `skills/network/segmentation/` | NIST SP 800-207, CIS Controls v8 |
  200. | DNS Security | `skills/network/dns-security/` | NIST SP 800-81, CIS Controls v8 |
  201. ### DevSecOps
  202. | Skill | Path | Frameworks |
  203. |-------|------|------------|
  204. | Pipeline Security | `skills/devsecops/pipeline-security/` | SLSA v1.0, OWASP CI/CD Top 10 |
  205. | Secrets Management | `skills/devsecops/secrets-management/` | OWASP Secrets Mgmt, NIST SP 800-57 |
  206. | SAST Configuration | `skills/devsecops/sast-config/` | OWASP ASVS, CWE Top 25 |
  207. | DAST Configuration | `skills/devsecops/dast-config/` | OWASP Top 10, OWASP Testing Guide |
  208. ---
  209. ## Role Bundles
  210. Pre-configured skill sequences for common security roles. Each bundle orchestrates skills in the right order for the engagement type.
  211. | Role | Description | Skills |
  212. |------|-------------|--------|
  213. | **vCISO** | Security program leadership, risk assessment, compliance, board reporting | nist-csf-assessment, soc2-gap, iam-review, cve-triage, threat-modeling |
  214. | **SOC Analyst** | Alert triage, threat hunting, incident investigation, detection engineering | alert-triage, detection-engineering, ir-playbook, log-analysis, cve-triage |
  215. | **Security Engineer** | Building security into products and infrastructure | secure-code-review, dependency-scanning, cve-triage, secrets-management, pipeline-security, container-security, iam-review |
  216. | **AppSec Engineer** | Application security design, testing, and code review | threat-modeling, secure-code-review, api-security, dependency-scanning, prompt-injection, owasp-top-10-web |
  217. | **Cloud Security Engineer** | Cloud posture, IaC review, container security, identity | aws-review, azure-review, gcp-review, iac-security, container-security, zero-trust-assessment, privileged-access |
  218. ---
  219. ## What Makes This Different
  220. - **Framework-grounded.** Every skill cites real control IDs from OWASP, NIST, MITRE ATT&CK, or CIS. No invented controls. No hallucinated references.
  221. - **Consistent output format.** Structured findings with severity, CWE mapping, framework reference, evidence, remediation, and normalized JSON -- every time.
  222. - **AI-security skills that don't exist elsewhere.** OWASP LLM Top 10, Agentic AI security, prompt injection testing, model supply chain review.
  223. - **Multi-agent compatible.** Same skill file works with Claude Code, Gemini CLI, Cursor, Codex CLI, OpenClaw, and Kiro.
  224. - **Prompt-injection hardened.** Every skill reviewed against OWASP LLM01:2025. CI scans for injection patterns on every PR.
  225. - **Enterprise-ready.** Built by practitioners, not scraped from blog posts. Designed for real security programs.
  226. ---
  227. ## Disclaimer
  228. These skills were built through extensive research against published security frameworks (OWASP, NIST, MITRE ATT&CK, CIS Controls) and reviewed by five specialized AI security agents:
  229. - **CISO Reviewer** — Strategic risk, compliance alignment, and program-level gaps
  230. - **Security Architect** — Framework accuracy, control ID verification, and design patterns
  231. - **Security Engineer** — Implementation correctness, tooling gaps, and operational feasibility
  232. - **AI Security Researcher** — LLM/agentic threat modeling, prompt injection hardening, and ATLAS coverage
  233. - **SOC Analyst** — Detection engineering, alert triage accuracy, and incident response workflows
  234. Despite this multi-layered review process, these skills may contain inaccuracies, outdated framework references, or gaps in coverage. **Validate all control IDs, framework versions, and remediation guidance against authoritative sources before using these skills in production security workflows.** Security frameworks evolve — always cross-reference with the latest published versions.
  235. ---
  236. ## Contribute
  237. Contributions are welcome — skill reviews, improvements, and new skills. Read **[CONTRIBUTING.md](CONTRIBUTING.md)** for the quality bar, skill-format specification, and the review/PR checklist, and author new skills with **[SKILL_TEMPLATE.md](SKILL_TEMPLATE.md)**. Every skill must cite a real framework with verifiable control IDs.
  238. > **⏸️ Bounty program paused.** The paid bounty program is temporarily on hold. Contributions are still welcome and will be credited — we'll announce on [Discord](https://discord.gg/DKTZzfU9B) when bounties resume.
  239. ## Security
  240. See [SECURITY.md](SECURITY.md) for our prompt injection hardening policy and responsible disclosure process.
  241. ## License
  242. [MIT](LICENSE)

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.