ai-security - Assess AI and LLM security risks
Assesses AI/ML systems for prompt injection, jailbreaks, model inversion, data poisoning, agent tool abuse, and MITRE ATLAS mappings.
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
Inputs
- Test prompts
- Prompt test file
- Target type
- Access level
- Threat scope
- Authorization status
Outputs
- Scan findings
- Risk scores
- MITRE ATLAS mappings
- Guardrail recommendations
- Exit status
Requirements
- Python 3 runtime
- Access to test prompts
- Written authorization for gray-box testing
- Written authorization for white-box testing