An offensive engine and an audit toolkit.

A penetration-testing platform that runs as a coordinated multi-agent system — specialist agents for reconnaissance, exploitation, and reporting handing work to each other through native tool calling, with structured output for findings.

• Multi-agent pipeline with native LLM tool calling
• Prompt-injection detection on untrusted target output
• Cost tracking and prompt caching across the run
• Structured, schema-validated reporting

Where CyberAI attacks, MST inspects. It probes agentic systems from the outside: speaking their protocols, fingerprinting their behaviour, and mapping what it finds to a recognised threat taxonomy — emitting SARIF so results drop into existing security pipelines.

• A2A protocol client for agent-to-agent surface testing
• MCP audit with JSON-RPC 2.0 codec and SARIF output
• ABFP behavioural fingerprinting engine
• Unified threat engine + CLI · AGPL-3.0

Detection covers the full OWASP Agentic Top 10:

1. ASI01 Agent Goal Hijack
2. ASI02 Tool Misuse & Exploitation
3. ASI03 Agent Identity & Privilege Abuse
4. ASI04 Agentic Supply Chain Compromise
5. ASI05 Unexpected Code Execution
6. ASI06 Memory & Context Poisoning
7. ASI07 Insecure Inter-Agent Communication
8. ASI08 Cascading Agent Failures
9. ASI09 Human-Agent Trust Exploitation
10. ASI10 Rogue Agents