Ai Security
Assesses AI/ML systems for security vulnerabilities including prompt injection, jailbreaks, model inversion, data poisoning, and agent tool abuse. Maps findings to MITRE ATLAS techniques and recommends guardrail controls for LLMs, classifiers, and embedding models.
- skills.sh installs
- 720
- GitHub stars
- 29.5K
- last updated
- Aug 21, 2026
Install
$ npx -y skills add alirezarezvani/claude-skills --skill ai-security --agent claude-codeInstalls into .claude/skills of the current project.
Files
AI Security
AI and LLM security assessment skill for detecting prompt injection, jailbreak vulnerabilities, model inversion risk, data poisoning exposure, and agent tool abuse. This is NOT general application security (see security-pen-testing) or behavioral anomaly detection in infrastructure (see threat-detection) — this is about security assessment of AI/ML systems and LLM-based agents specifically.
Table of Contents
- Overview
- AI Threat Scanner Tool
- Prompt Injection Detection
- Jailbreak Assessment
- Model Inversion Risk
- Data Poisoning Risk
- Agent Tool Abuse
- MITRE ATLAS Coverage
- Guardrail Design Patterns
- Workflows
- Anti-Patterns
- Cross-References
Overview
What This Skill Does
Sponsors
Promote your product hereReach 125k+ visitors monthlyPromote your product hereReach 125k+ visitors monthly
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any language
Agent CaffeineSponsoredClose your lid, come back to finished workSnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthlyWaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthlyknobsSponsoredSee your site on any phone, any day, in any languageDetails
- Repository
- github.com/alirezarezvani/claude-skills
- Categories
- Security, AI & Agent Building, Data Science & ML
- First seen
- Jun 3, 2026
More from alirezarezvani/claude-skills
All 267- Brand Guidelines720
- Docker Development720
- Content Strategy719
- Dependency Auditor711
- Page Cro709
- Llm Wiki706
- Secrets Vault Manager705
- Agent Designer703
- Ci Cd Pipeline Builder702
- Pr Review Expert701
- Product Analytics700
- Apple Hig Expert692
- Atlassian Admin691
- Atlassian Templates691
- Saas Metrics Coach690
- Social Content690
- Observability Designer688
- Founder Coach687
- Playwright Pro687
- Pricing Strategy687
- Env Secrets Manager685
- Competitive Teardown684
- Interview System Designer684
- Seo Audit678
Recommended
More Security1
clerk-authenticationmindrally/skillsGuidelines for implementing Clerk authentication in Next.js applications with middleware, hooks, and security best practices707skills.sh installs
clerk-authenticationmindrally/skillsGuidelines for implementing Clerk authentication in Next.js applications with middleware, hooks, and security best practices707skills.sh installs2
securitytartinerlabs/skillsUse when auditing security, checking for vulnerabilities, scanning for secrets, or reviewing dependencies. OWASP Top 10 audit with GitLeaks and dependency check561skills.sh installs
securitytartinerlabs/skillsUse when auditing security, checking for vulnerabilities, scanning for secrets, or reviewing dependencies. OWASP Top 10 audit with GitLeaks and dependency check561skills.sh installs3
vulnerability-scanningsecondsky/claude-skillsAutomated security scanning for dependencies, code, containers with Trivy, Snyk, npm audit. Use for CI/CD security gates, pre-deployment audits, compliance requ534skills.sh installs
vulnerability-scanningsecondsky/claude-skillsAutomated security scanning for dependencies, code, containers with Trivy, Snyk, npm audit. Use for CI/CD security gates, pre-deployment audits, compliance requ534skills.sh installs4
security-scanjwynia/agent-skillsScan code for security vulnerabilities including OWASP Top 10, secrets, and misconfigurations. Use when you need comprehensive security analysis of a codebase.487skills.sh installs
security-scanjwynia/agent-skillsScan code for security vulnerabilities including OWASP Top 10, secrets, and misconfigurations. Use when you need comprehensive security analysis of a codebase.487skills.sh installs5
xss-preventionaj-geddes/useful-ai-promptsPrevent Cross-Site Scripting (XSS) attacks through input sanitization, output encoding, and Content Security Policy. Use when handling user-generated content in482skills.sh installs
xss-preventionaj-geddes/useful-ai-promptsPrevent Cross-Site Scripting (XSS) attacks through input sanitization, output encoding, and Content Security Policy. Use when handling user-generated content in482skills.sh installs6cloud-security-configurationaj-geddes/useful-ai-promptsImplement comprehensive cloud security across AWS, Azure, and GCP with IAM, encryption, network security, compliance, and threat detection.472skills.sh installs
cloud-security-configurationaj-geddes/useful-ai-promptsImplement comprehensive cloud security across AWS, Azure, and GCP with IAM, encryption, network security, compliance, and threat detection.472skills.sh installs