Microsoft's policy enforcement, identity, sandboxing and audit logging for autonomous AI agents.
pip install "agent-governance-toolkit[full]"The toolkit puts hard controls around agents. A YAML policy engine intercepts every tool call before it runs, and the toolkit adds zero-trust identity, execution sandboxing and audit logs.
pip install "agent-governance-toolkit[full]"
In Claude Code: /plugin marketplace add microsoft/agent-governance-toolkit.
NVIDIA · Tool / CLI
NVIDIA's security scanner for agent skills that finds vulnerabilities, prompt injection and malicious patterns before you install a skill.
Strix · Agent
Open-source AI penetration testers that run your app, find vulnerabilities and prove each one with a working exploit.
Keygraph · Agent
An autonomous AI pentester for web apps and APIs that only reports the vulnerabilities it can prove with a working exploit.