Radar / AI security / Arcjet AI security models
Arcjet AI security models: custom prompt-injection detectors for coding agents
Arcjet ships a family of compact, custom-trained security models that catch prompt injection in AI agent activity.
Why it matters
First purchasable detector family built specifically for coding agents, tuned to tell legitimate dev activity apart from malicious instructions hidden in tool outputs.
What you could build with it
A small dev-tools team could wire Himalia 1 into its coding agent's tool-call loop, blocking or flagging any shell command whose arguments came from untrusted web or repo content, and measure how many real attacks it stops versus false alarms over a month.
Does it hold up?
Too early to judge: Himalia 1 is live in Arcjet's SDKs from day one, so existing Arcjet users get it automatically, but independent accuracy reports from coding-agent teams have not appeared yet.
Built with Arcjet AI security models
- Arcjet launches custom AI security models to protect AI agentsprnewswire · Press release announcing Himalia 1 generally available and Thebe 1 and Carme 1 in early access.
- By Jupiter, Arcjet on why coding agents need prompt injection detectorscomputerweekly · Computer Weekly coverage of the launch, including the Qwen3-0.6B classifier base and the three specialist detectors.
- AI Security Models for Coding Agents — trend reportaimfast · Trend analysis framing the launch as the moment agent prompt-injection detection became a purchasable product category.
Learn more
First spotted on article: source.
More AI security
NVIDIA SkillSpector: security scanner for AI agent skills, trending againNVIDIA's open-source SkillSpector scanner is trending on GitHub today: it audits AI agent skills before installation…security · JEV 0.75Cloudflare security-audit-skill: turn your coding agent into a security auditorA coding-agent skill for multi-phase security audits with independently verified, machine-readable findings.security · JEV 0.72Shannon: open-source AI pentester that reports only vulnerabilities it can actually exploitCLI agent that combines source-code analysis with live exploitation against web apps and APIs under a 'no exploit, no…security · JEV 0.71AiSOC: open-source AI security operations center with agent triageSelf-hosted SOC that fuses alerts into incidents and hands them to LLM agents that record every prompt and tool call…security · JEV 0.71Codex Security 0.10.0: OpenAI's agentic vulnerability scanner adds resumable scans and cost budgetsOpenAI released Codex Security 0.10.0 on 12 Nov 2026: the open-source CLI and TypeScript SDK that builds a threat…security · JEV 0.69iFixAi: independent auditing of AI agents in under 120 secondsiFixAi audits whether an AI agent is doing what it is supposed to do, run by a human or by the agent itself, answering…security · JEV 0.68
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.