Integrations / Data protection engine

Argent with an ONNX injection classifier

Argent scores prompts for injection and jailbreak attempts with a small classifier model that runs in ONNX inside your own deployment. It runs on plain CPUs, the weights are fetched and pinned by you, and no text is sent anywhere to be judged.

A processor chip with one line of text flagged in oxblood
01 / INTEGRATIONS / DATA PROTECTION ENGINE

What Argent does with the classifier

A prompt-injection check that runs on the machines you already have.

OWASP ranks prompt injection first, as LLM01, in its Top 10 for LLM Applications 2025 (OWASP GenAI Security Project). The UK National Cyber Security Centre warns that prompt injection is not SQL injection and may be worse (NCSC, December 2025).

ONNX is an open format for machine-learning models. Argent serves injection models in it from a sidecar next to the gateway.

  • One pass per text. The model gives one injection probability, which Argent applies to both the prompt_injection and jailbreak categories.
  • Scores what a person wrote. Argent pulls out the prompt text before scoring, so the JSON around it is not mistaken for an attack.
  • Long prompts in windows. A long prompt is scored in overlapping windows, and the verdict is the highest window. Text past the window cap is marked unscored, never assumed safe.
  • Blocks or watches. Above your threshold, a prompt is refused before it reaches the model, or, in observe mode, scored and recorded without blocking.
02 / INTEGRATIONS / DATA PROTECTION ENGINE

The models it serves

One sidecar can serve several models. Each has reviewed pins and a known license.

ModelLicenseRuns on
ProtectAI deberta-v3-base-prompt-injection-v2Apache-2.0CPU. The default injection model on GPU installs
PIGuardMITCPU
Horizon prompt-injection-guard-baseApache-2.0CPU
  • Pinned to a revision. Every model is fetched at a pinned revision and every file is checked against its SHA-256. The sidecar refuses a model whose revision does not match.
  • No remote code at run time. Where a model needs export code, it runs once on the operator's machine during export, never inside the sidecar.
  • Checked export. Models converted to a smaller format are compared with the original, and an export whose verdicts change is refused.
03 / INTEGRATIONS / DATA PROTECTION ENGINE

How it connects

The classifier is a service inside your Argent deployment. Nothing leaves it.

Where it runsA sidecar service beside the gateway, onnx-classifier on port 8080
CallsThe gateway posts text to /score; /models lists each loaded model with its revision and hash
Docker ComposeThe classifier-onnx profile, or classifier-onnx-gpu on a GPU machine
Helmclassifier.onnx.enabled=true; a fetch Job pulls the models
WeightsFetched by you and never baked into any image
04 / INTEGRATIONS / DATA PROTECTION ENGINE

What you configure

Fetch the weights, switch the sidecar on, pick the model, then set the policy.

  1. Accept the license and fetch. Run make accept-onnx-license, then make fetch-onnx-model. In Helm, the fetch Job runs only once classifier.onnx.fetch.licenseAccepted=true is set.
  2. Switch the sidecar on. Use the Compose profile or the Helm value above.
  3. Pick the model. A CPU-only install ships with no default classifier, and the console says so plainly until an admin picks one. A GPU install defaults to the ProtectAI model for injection.
  4. Set the tenant's classifier policy. On the Classifier page: which categories, the block threshold, block or observe, what happens on a timeout, and on or off.
  5. Watch first. In watch, would-be blocks are recorded and nothing is refused. Switch to enforce when the record looks right.

Air-gapped? This is the recommended classifier for CPU-only and air-gapped installs: no GPU, no outside call. See Air-Gapped Install.

05 / INTEGRATIONS / DATA PROTECTION ENGINE

Honest about what it scored

A prompt that was not scored is recorded as not scored. It is never recorded as clean.

  • No model, no false comfort. Tenants with no model picked are recorded as not scored, never as clean, and are never blocked for it.
  • Unknown model fails closed. A request for a model the sidecar does not have is treated as could not measure.
  • Every change is announced. When a deployment default takes effect for a tenant, Argent signs one event naming the model, and the tenant keeps its own watch or enforce setting.
06 / INTEGRATIONS / DATA PROTECTION ENGINE

Where this fits