ai-security-verification — Claude Code skill: what it does
ai-security-verification evaluates AI apps and LLM pipelines against the OWASP AISVS framework across 13 security categories.
CC-BY-4.0 152 installs ★ 230 updated 2026-10-15
npx skills add OWASP/secure-agent-playbook --skill ai-security-verification -a claude-codeWhat ai-security-verification does
This skill guides security assessments for AI systems using the OWASP AI Security Verification Standard. It reviews 13 distinct areas, covering training data governance, prompt injection defenses, model lifecycle controls, vector storage isolation, and agent tool execution.
Audits yield structured reports based on templates/finding.md. The output details control evaluations, gap analyses, prioritized risk lists, and a compliance roadmap supported by evidence documentation.
Because the execution steps rely on plays/ai-security-verification.md, the agent must have access to the playbook files within the repository.
What it helps with
- verify an AI system against the OWASP AISVS framework
- evaluate prompt injection defenses and adversarial input resilience
- audit agent orchestration rules and tool permissions
- generate a prioritized security compliance roadmap
Example prompts for the agent
- Run an OWASP AISVS security verification on our AI agent
- Check our vector database and prompt validation against AISVS controls
- Generate an AI security gap analysis report using the finding template
How to install ai-security-verification
1Skills CLI (Vercel)
npx skills add OWASP/secure-agent-playbook --skill ai-security-verification -a claude-code2Manually: put the files in place
~/.claude/skills/ai-security-verification/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/ai-security-verification/
1Skills CLI (Vercel)
npx skills add OWASP/secure-agent-playbook --skill ai-security-verification -a codex2Manually: put the files in place
.agents/skills/ai-security-verification/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add OWASP/secure-agent-playbook --skill ai-security-verification -a cursor2Manually: put the files in place
.cursor/skills/ai-security-verification/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install OWASP/secure-agent-playbook plugins/ai-security-skills/skills/ai-security-verification2Manually: put the files in place
.github/skills/ai-security-verification/SKILL.md1Skills CLI (Vercel)
npx skills add OWASP/secure-agent-playbook --skill ai-security-verification -a gemini-cli2Platform CLI
gemini skills install https://github.com/OWASP/secure-agent-playbook --path plugins/ai-security-skills/skills/ai-security-verificationManually: put the files in place
.devin/skills/ai-security-verification/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add OWASP/secure-agent-playbook --skill ai-security-verification -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about ai-security-verification
How do I install ai-security-verification in Claude Code?
Run npx skills add OWASP/secure-agent-playbook --skill ai-security-verification -a claude-code.
What does ai-security-verification do?
It runs an audit across 13 AI security categories, evaluating input validation, model supply chains, autonomous actions, and logging.
What output does the verification produce?
It outputs finding files matching templates/finding.md with an assessment status, risk gap analysis, and a structured remediation roadmap.
Source text
SKILL.md · CC-BY-4.0
--- name: ai-security-verification description: Comprehensive AI security verification using OWASP AI Security Verification Standard (AISVS) framework. Use when verifying an AI-driven application, ML pipeline, or LLM-integrated system against AISVS, preparing for an AI security audit, or checking security and ethical controls across 13 categories from training data governance to human oversight. license: CC-BY-4.0 --- # AI Security Verification Standard (AISVS) Conduct comprehensive security verification of AI-driven applications using the OWASP AI Security Verification Standard (AISVS) framework's 13-category structured checklist. Follow the full procedure in `plays/ai-security-verification.md`. ## Steps 1. **Training Data Governance & Bias Management** — Assess data quality, provenance, bias detection, and governance controls throughout the data lifecycle. 2. **User Input Validation** — Evaluate input sanitization, prompt injection defenses, adversarial input detection, and boundary validation mechanisms. 3. **Model Lifecycle Management & Change Control** — Review model versioning, deployment controls, rollback capabilities, and change management processes. 4. **Infrastructure, Configuration & Deployment Security** — Examine deployment security, container hardening, network controls, and infrastructure configuration. 5. **Access Control & Identity** — Verify authentication mechanisms, authorization controls, privilege management, and identity governance. 6. **Supply Chain Security for Models, Frameworks & Data** — Assess third-party model security, dependency management, and supply chain integrity. 7. **Model Behavior, Output Control & Safety Assurance** — Evaluate output validation, safety guardrails, behavior monitoring, and harmful content prevention. 8. **Memory, Embeddings & Vector Database Security** — Review vector database security, embedding protection, memory isolation, and context management. 9. **Autonomous Orchestration & Agentic Action Security** — Assess agent coordination security, tool access controls, and autonomous decision-making safeguards. 10. **Adversarial Robustness & Attack Resistance** — Test resilience against adversarial examples, evasion attacks, and model extraction attempts. 11. **Privacy Protection & Personal Data Management** — Verify privacy controls, data minimization, consent management, and regulatory compliance. 12. **Monitoring, Logging & Anomaly Detection** — Evaluate security monitoring, audit logging, anomaly detection, and incident response capabilities. 13. **Human Oversight and Trust** — Assess human-in-the-loop controls, explainability mechanisms, and trust calibration measures. ## Output Use the finding format from `templates/finding.md`. Produce: - **AISVS Compliance Assessment** — Verification status across all 13 categories - **Security Control Evaluation** — Detailed analysis of implemented controls - **Gap Analysis** — Missing or inadequate security measures - **Risk-Based Prioritization** — Critical findings requiring immediate attention - **Compliance Roadmap** — Structured plan to achieve AISVS compliance - **Verification Evidence** — Documentation supporting compliance claims ## OWASP References - **OWASP AI Security Verification Standard (AISVS)** - OWASP Top 10 for LLM Applications 2025 - OWASP AI Security and Privacy Guide - OWASP Application Security Verification Standard (ASVS) - OWASP AI Testing Guide - Full procedure: `plays/ai-security-verification.md`
© OWASP · CC-BY-4.0 · OWASP/secure-agent-playbook