Map / Runtime & Guardrails / Rogue Security
Rogue Security
rogue.security ↗ · LinkedIn ↗ · Open on the map
Runtime & GuardrailsAI CSPMMCP & LLM GatewaysAI Red Teaming
Capabilities
AI agent runtime security across four pillars: AI-SPM (shadow AI discovery, agent inventory/classification), AIDR (detection & response), AI AppSec (build-time/CI-CD testing with the Rogue OSS red-team engine), and Access Control (approval + enforcement). RISC intent-classification engine flags malicious agent actions in milliseconds; Sentinel V2 model published as OSS on HuggingFace.
Sensors / integration
In-VPC deployment with zero data egress; endpoint + SaaS shadow-AI discovery, agent/MCP inventory, behavioral anomaly detection on agent workflows, CI/CD integration.
Protections
Runtime guardrails at sub-5ms latency, prompt injection and jailbreak blocking, tool-abuse and privilege-escalation blocking, granular per-tool MCP permissions instead of all-or-nothing, remote removal of unapproved skills/MCP entries, automated containment.
Differentiator
Focused first on coding agents (agents that ship code and hold production permissions); intent classification runs entirely inside the customer VPC. Rebranded from Qualifire (LLM evaluation and guardrails); the open-source Rogue agent-evaluation engine built there became the red-team layer of the security product.
Team & funding
- Founders
- Ariel Dan, Dror Ivry, Gilad Ivry
- Total raised
- $4.6M
- Investors
- Disruptive AI, AnD Ventures
- Previously
- Qualifire
Other Runtime & Guardrails companies
AariaSec · ActaClad · ActiveFence · Acuvity · AGAT Software · AgentFox · AI Aramid · AI Prompt Shield · Aiceberg · Aim Security · AIR · Aira Security · See all →
Last updated · Get the “Listed on” badge