#agent-security

Open detection standard -- like Sigma, but for AI agents. 425 rules, shipped in Microsoft AGT, Cisco AI Defense, MISP, OWASP A-S-R-H. 97.1% recall on NVIDIA garak. NIST OSCAL Path 1.

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

The leaked Anthropic reasoning protocol. Running locally. Zero-drift coding with Strict Write Discipline and adaptive Claude Opus 4.8 thinking. Mythos

Agent Beacon is the world's first open-source telemetry layer for AI agents wherever they run: locally, in CI, or in the cloud.

Active security scanner for A2A and MCP servers

Receipt Required for AI agents — no receipt, no irreversible action. An open, offline-verifiable authorization-receipt protocol: a named human signs the exact high-risk action (payment, deploy, delete, permissions) before it runs, and anyone can verify it later, trusting no one. Apache-2.0 · formally verified · IETF Internet-Drafts.

540 security tests for AI agent systems — MCP, A2A, x402/L402, decision governance, benchmark integrity, skill supply chain. AIUC-1 pre-cert, NIST AI 800-2 aligned, MCP tool-poisoning reproduction. v4.9.1

Open-source evidence layer for AI governance. Gates every AI agent tool call against your policy and writes a hash-chained execution record an auditor verifies offline, without trusting the operator. Root-agnostic, and binds to a TPM 2.0 or SEV-SNP hardware root when present. Your environment, no SaaS, no telemetry. AGPL-3.0.

Open-source security-first runtime for AI agents that learn and act across sessions.

Composable security scanning harness for agent skills

Runtime Firewall for AI agents which catches the rogue tool call before it runs. Dangerous commands, secret leaks, prompt injection. For Claude Code, Codex and framework SDKs

Open source authorization engine for AI agents. Confidence-aware gating · Human-in-the-loop review · Policy-as-code · Full audit trail

Static analyzer for agent reliability.

Опис репозиторію не опубліковано.