
nah
a guard that blocks catastrophic agent actions
ai-securitycode-analysiscommand-and-control+8
4812 days ago

a guard that blocks catastrophic agent actions

The Execution Security Layer for the Agentic Era. Providing deterministic "Sudo" governance and audit logs for autonomous AI agents.

Static security scanner for AI agent skill packages. Detects malicious SKILL.md files and bundled scripts before they run.

A CI/CD Red Team Framework for demonstrating Build Pipeline security risks.

Detects GlassWorm supply chain attack payloads by scanning VS Code extensions, npm/PyPI packages, and git repos for invisible Unicode payloads,…