ai-security - AI/ML and LLM Agent Security Assessment
Assesses AI/ML systems and LLM agents for prompt injection, jailbreaks, model inversion, data poisoning, and tool abuse.
Tags
Updated: 2026-10-03Capabilities
Typical Inputs
Typical Outputs
What this skill does
- Detect injection signatures
- Assess jailbreak resistance
- Score inversion risk
- Score poisoning risk
- Map findings to MITRE ATLAS
- Assess agent tool abuse
- Recommend guardrail controls
Inputs
- Test prompts
- Prompt test file
- Target type
- Access level
- Threat scope
- Written authorization
Outputs
- Injection findings
- Risk scores
- MITRE ATLAS mappings
- Guardrail recommendations
- Scanner exit status
- JSON scan report
Requirements
- Python 3 runtime
- AI threat scanner script
- Written authorization for gray-box or white-box testing