Stats
Actions
Tags
Help us improve
Share bugs, ideas, or general feedback.
From cybersec-toolkit
Reviews AI/LLM applications for security risks including prompt injection, RAG security, agent permissioning, jailbreaks, data leakage, and model supply chain threats.
npx claudepluginhub 26zl/cybersec-toolkit --plugin cybersec-toolkitHow this skill is triggered — by the user, by Claude, or both
Slash command
/cybersec-toolkit:ai-llm-security-reviewThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use this skill for AI applications, agents, RAG systems, model gateways, prompt chains, evals, and LLM governance.
Audit applications for AI prompt injection, agent security, and LLM permission boundary vulnerabilities. Use when securing AI features or agents.
Offensive checklist for AI/LLM security testing: prompt injection, jailbreaking, model extraction, training data poisoning, adversarial inputs, and LLM-assisted attack automation. Use for red-teaming and authorized security assessments of AI/ML systems.
Mitigate prompt injection risks in LLM-based systems. Use when designing, building, or reviewing AI systems that accept user prompts, or when evaluating model safety for deployment.
Share bugs, ideas, or general feedback.
Use this skill for AI applications, agents, RAG systems, model gateways, prompt chains, evals, and LLM governance.
Return findings as:
| Risk | Attack path | Impact | Evidence | Control | Test to keep fixed |
|---|
When the task involves current AI regulation or sector obligations, verify against current official sources before making definitive claims.