ai-security - Assess AI and LLM security risks
Assesses AI/ML systems for prompt injection, jailbreaks, model inversion, data poisoning, and agent tool abuse.
Tags
Updated: 2026-10-03AI securityLLM securityprompt injectionjailbreak detectionmodel inversiondata poisoningagent securityMITRE ATLAS
Capabilities
Typical Inputs
Typical Outputs
What this skill does
- Scan prompt injection signatures
- Assess jailbreak resistance
- Score model inversion risk
- Score data poisoning risk
- Detect agent tool abuse
- Map findings to MITRE ATLAS
- Recommend guardrail controls
- List injection signatures
Inputs
- Test prompts
- Prompt test file
- Target type
- Access level
- Threat category scope
- Written test authorization
Outputs
- Injection findings
- Risk scores
- MITRE ATLAS mappings
- Guardrail control recommendations
- Injection signature list
- Scanner exit status
Requirements
- Python 3 environment
- Written authorization for gray-box or white-box testing