MCP server + cross-harness skills for building and operating AI agents safely. Grounded in NIST AI RMF, CISA, OWASP, CUSTODY, LASM.
Skill Claude CodeCodex
Audit an AI agent deployment against the CUSTODY containment framework and LASM threat model. Checks identity, input handling, supervision, traceability, operational controls, dependency management, and yield/teardown. Maps findings to NIST AI RMF, OWASP, CUSTODY pillars, and LASM layers.
Skill Claude CodeCodex
Review a repository or project for AI harness security engineering safeguards. Checks architectural documentation, mechanical constraints, testing, review processes, and AI-specific safeguards. Maps findings to NIST AI RMF, OWASP, CUSTODY, and LASM.
Skill Claude CodeCodex
Plan and execute AI red team engagements using the OWASP AI Red Teaming Guide, MITRE ATLAS, PyRIT, and garak. Covers scoping, threat modeling, prompt injection, jailbreak, data exfiltration, tool misuse, agent autonomy, and multi-agent attacks. Produces structured findings mapped to OWASP, ATLAS, and NIST AI RMF.