Agent Threat Rules: Open detection rule format for AI agent security threats

Agent Threat Rules (ATR), an open detection format for AI agent security threats, has been released to address vulnerabilities such as prompt injection, tool poisoning, and credential theft in coding assistants, MCP servers, and multi-agent frameworks. The YAML-based, versioned schema aims to close the gap between public CVE feeds carrying agent-execution flaws and the tooling needed to catch them in production.

AI agents run inside coding assistants, MCP servers, and multi-agent frameworks, and the access that makes them useful also opens paths to prompt injection, tool poisoning, and credential theft. Public CVE feeds carry agent-execution flaws that reach production faster than the tooling built to catch them. Agent Threat Rules, or ATR, is an open detection format aimed at this category of attack. ATR rules are YAML documents that conform to a versioned schema. Each one … More https://www.helpnetsecurity.com/2026/06/03/agent-threat-rules-ai-detection/ The post Agent Threat Rules: Open detection rule format for AI agent security threats https://www.helpnetsecurity.com/2026/06/03/agent-threat-rules-ai-detection/ appeared first on Help Net Security https://www.helpnetsecurity.com .