Arcjet is the runtime security platform that ships in your AI code. Detect prompt injection, authorize agent tool calls, redact sensitive data, and block bots and abuse. Real-time security building blocks you call inside your app, before an action happens.
This is the 3rd launch from Arcjet. View more
Arcjet AI security models
Launched this week
Arcjet is launching a family of custom AI security models designed for analyzing AI agent activity: Arcjet Himalia 1, a general purpose prompt injection model, live today for every SDK call that uses prompt injection detection, and specialist versions designed for situations that general models handle badly, Arcjet Thebe 1 for coding agents, and Arcjet Carme 1, for autonomous security agents.
Launch Team
CloudflareYour next app belongs on Cloudflare Workers. Deploy for free
Promoted
When the small model flags a step and the big model is reading the whole session, does the agent pause and wait, or keep going while that check runs? If it keeps going, a couple of risky calls could land before the verdict comes back.
@0x47xavier we do both synchronous and asynchronous analysis, so we can block individual actions and continually scan the overall session. Analysis happens in 10s or low 100s of milliseconds, so there is minimal latency blocking the coding agent whilst it's waiting for a response.
Low 100s of ms is fine for a pause. What I'd want to see is the session-scan side. If it flags something three steps later, does the agent get told which earlier step tripped it, or does it just get stopped?
If Himalia flags a prompt injection inside a tool result mid run, does it block just that tool output or kill the whole agent session?
@igorblink if Arcjet detects prompt injection in the tool result for coding agents, subsequent risky actions are blocked, but not the whole session. This allows the session to continue locally, but prevent the true risky actions. For custom agents where you use our SDK, you can decide how you want to proceed. You get the full result back into code so you can choose how the manage the detectors.
How does Thebe handle security tests that deliberately contain prompt injections? Curious how it distinguishes the test data from instructions aimed at the agent.
@marianna_tymchuk the training datasets are different, so we have specifically labeled training data and evals to help with accuracy. Then a secondary decision model runs on all the detections to understand the context. The prompt detection (from the prompt, tool output, API calls, etc) runs first and then the decision model evaluates whether it's a true attack or not. It's that second step that understands the context e.g. test files containing attack evals.
Using small classifiers that return a verdict in milliseconds, with a larger model only on suspicious hits, is a sensible split. How often does that second decision step end up running in a typical session?
@neerajnathany the second decision is triggered by a detection from the first model. This is detect and verify, with two specialist models working on different context. That helps to reduce false positives.
The distinction between Himalia being live and the specialist models being in preview is useful. Keeping the model version visible with each verdict would help teams compare behavior as those previews develop.
Super clean approach to AI agent security! Stopping unauthorized actions right at the code level is definitely the way to go
Wishing you all the best with the project!