Agent skill · security · alirezarezvani
ai-security
Use when assessing an AI/ML system or LLM agent for prompt injection, jailbreaks, model inversion, data poisoning or tool abuse. Maps findings to MITRE ATLAS and scores robustness with ai_threat_scanner.py.
Why this skill is useful
Adds a specialized tool for scanning AI/ML systems for vulnerabilities, including executable scripts for risk assessment and MITRE ATLAS mapping.
What it needs
Requires python3 installed locally. About 10k tokens when loaded. Last updated 2026-08-05. 23,939 stars on the source repository.
What this skill does
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 This skill provides the methodology and tooling for AI/ML security assessment — scanning for prompt injection signatures, scoring model inversion and data poisoning risk, mapping findings to MITRE ATLAS techniques, and recommending guardrail controls. It supports LLMs, classifiers, and embedding models. Distinction from Other Security Skills Skill Focus Approach ------- ------- ---------- ai-security (this) AI/ML system security Specialized — LLM injection, model inversion, ATLAS mapping security-pen-testing Application vulnerabilities General — OWASP Top 10, API security, dependency scanning red-team Adversary simulation Offensive — kill-chain planning against infrastructure threat-detection Behavioral anomalies Proactive — hunting in telemetry, not model inputs Prerequisites Access to test prompts or a prompt test file (JSON array). For gray-box and white-box access levels, written authorization is required before testing. The tool uses static signature matching and does not require live model access — it assesses inputs before they reach the model. --- AI Threat Scanner Tool The aithreatscanner.py tool scans prompts for injection signatures, scores model-level risks, and maps findings to MITRE ATLAS techniques. Test File Format Accepts plain strings or objects with a "prompt" key. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills alirezarezvani/ai-security--d8fa82