Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →alirezarezvani/ai-security
Use when assessing AI/ML systems for prompt injection, jailbreak vulnerabilities, model inversion risk, data poisoning exposure, or agent tool abuse. Covers MITRE ATLAS technique mapping, injection signature detection, and adversarial robustness scoring.
Passed 23 of 24 test cases with the skill, and 14 of 24 without it.
and 7 more in the full report
9 fixed15 passed either way1 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
Which CLI option should I pass to the python threat scanner tool to display all available injection signature pattern names along with their mapped ATLAS technique IDs without running a full scan?
| Checked | Without skill | With skill |
|---|---|---|
| --list-patterns | Missed | Passed |
The instructions your model reads when the skill loads.
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.
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.
| 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 |
test cases passed, vs 14 / 24 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.