Portable security rules for the action boundary of AI agents
-
Updated
Jul 15, 2026 - Rust
Portable security rules for the action boundary of AI agents
The zero-trust framework for autonomous AI agents.
Maps an AI coding agent's actions — or a repository — to OWASP Agentic Top 10 and compliance framework controls, surfacing candidate findings with citations. Rust scanner + agent skill, SARIF output.
SPIFFE/WIMSE URI parsing library. Standalone, zero-dep.
Add a description, image, and links to the agentic-security topic page so that developers can more easily learn about it.
To associate your repository with the agentic-security topic, visit your repo's landing page and select "manage topics."