cosai-oasis/secure-ai-tooling
The CoSAI Risk Map is a framework for identifying, analyzing, and mitigating security risks in Artificial Intelligence systems. As traditional software security practices are not always sufficient for AI, this project provides a shared understanding and a common language for addressing the unique security challenges of the AI development lifecycle.
The framework organizes AI security across four lifecycle dimensions—Data, Infrastructure, Model, and Application—with structured catalogs of components, risks, controls, and personas mapped to human-readable YAML and machine-parseable JSON schemas. It includes cross-referencing with established frameworks like MITRE ATLAS, NIST AI RMF, STRIDE, and OWASP Top 10 for LLM, enabling alignment with existing compliance standards. The approach extends threat modeling beyond isolated model vulnerabilities to systemic risks across data pipelines, infrastructure, and deployment ecosystems.
Stars
65
Forks
19
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 11, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/cosai-oasis/secure-ai-tooling"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related agents
Nebulock-Inc/agentic-threat-hunting-framework
ATHF is a framework for agentic threat hunting - building systems that can remember, learn, and...
AgentSeal/agentseal
Security toolkit for AI agents. Scan your machine for dangerous skills and MCP configs, monitor...
HeadyZhang/agent-audit
Static security scanner for LLM agents — prompt injection, MCP config auditing, taint analysis....
oasm-platform/open-asm
Open-source platform for cybersecurity Attack Surface Management (OASM).
affaan-m/agentshield
AI agent security scanner. Detect vulnerabilities in agent configurations, MCP servers, and tool...