Kirin (Knostic)

Coding-agent runtime security and governance enforcement product. Targets Cursor, GitHub Copilot, and other AI-coding IDEs. Per the Knostic blog post, Kirin’s stated capabilities:

CapabilityMaps to Agentic AI Security Capability Maturity Model — A 2026 Practical Proposal
Hidden prompt-injection detection in code/contextD4 Runtime & Guardrails
Malicious agent rules-file analysis (Cursor / Copilot rules)D6 Data, Memory & RAG (Cognitive File Integrity extension to rules files)
Rogue IDE extension detectionD8 Supply Chain & AI-BOM
Typosquatted package blockingD8 Supply Chain & AI-BOM
MCP server validation + CVE checksD5 Egress & Network, D8 Supply Chain
Destructive agent action blockingD3 Control & Least-Agency
Continuous policy enforcement at runtimeD4 Runtime, D7 Observability
Single dashboard tracking MCP usage, rule changes, policy violationsD7 Observability & Detection

Where Kirin sits in the Agentic AI Security Reference Architecture (2026)

A coding-agent-specific overlay that touches the Runtime, Egress, Data (rules files), and Observability planes. Conceptually similar to a coding-agent EDR. Closest OSS analogue is LlamaFirewall (PromptGuard 2 + AlignmentCheck + CodeShield), which Kirin is not directly comparable to but plays an adjacent role.

Strengths / Weaknesses

Strengths: targets coding-agent-specific threats (rules-file poisoning, IDE extension marketplace, typosquats) that broader AI security platforms don’t sharpen on. Single dashboard for MCP/rule/policy view.

Weaknesses (vendor-marketing-stated, uncorroborated): not benchmark-published; no AgentDojo-class evaluation cited; no head-to-head with LlamaFirewall, AgentGateway, or Cursor’s own Rulesets enforcement.

Relations