Default-deny execution gate for AI agents, APIs, and distributed systems. Policies, drift detection, hard invariants, post-quantum signed permits.Written in Rust. Says no unless policy says yes.
-
Updated
May 4, 2026 - Rust
#
agentsecurity
Here are 2 public repositories matching this topic...
Local-first capability discovery for AI agent workspaces. Scans your skills, MCP servers, and scripts to find risky combinations (e.g. read .env + post to webhook = data exfiltration) — no LLM calls, no uploads. CLI + HTML report + chat summary for personal agents like Hermes and OpenClaw.
-
Updated
May 14, 2026 - TypeScript
Improve this page
Add a description, image, and links to the agentsecurity topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the agentsecurity topic, visit your repo's landing page and select "manage topics."