Check Point AI Agent Security (formerly Lakera Guard)
Runtime protection for AI agents that inspects prompts, reference material, tool responses and tool descriptions for injections and manipulation, applies tool allow and deny lists, and flags actions outside an agent's mandate. Also builds an inventory of agents and connected MCP servers across supported agent platforms.
commercial · generally available · Research snapshot 2026-09-06
Show me Check Point AI Guardrails detecting an injection hidden in a tool response and blocking the resulting tool call, plus the agent inventory entry for that agent's MCP servers.
Capabilities and evidence
Support labels reflect the supplied research. Documentation and vendor claims are not independent product tests. “Not established” means the researcher did not find support; it does not prove a capability is absent.
Documented by provider
Documentation states detection of prompt injections, jailbreaks and manipulation in user prompts, reference materials, tool responses and tool descriptions across the agentic workflow.
Limit: Detection accuracy rates and supported languages are not stated on the fetched page.
The product connects to agent platforms and cloud infrastructure to build a continuously updated inventory of agents, their tools and connected MCP servers, with risk ratings mapped to OWASP and MITRE ATLAS.
Limit: Coverage is limited to the listed supported platforms.