Skip to content

Red Team Framework

The Arbitex Red Team Framework is an automated adversarial testing tool for AI applications protected by Arbitex. It systematically probes your deployment for vulnerabilities — prompt injection, data exfiltration bypasses, and supply chain attacks — before real attackers find them first.

Rather than waiting for a security incident, you run the framework against your deployment on a schedule or as part of your CI/CD pipeline, measure your Attack Success Rate (ASR), and block deployments that exceed your risk tolerance.


Probe library: 152 probes across 3 categories

Section titled “Probe library: 152 probes across 3 categories”

Tests whether an attacker can override your system prompt or redirect model behavior through crafted user input.

Probe type What it tests
Direct injection Explicit override attempts in user messages
Indirect injection Injections embedded in retrieved documents, tool outputs, or external data
Instruction override Attempts to cancel or supersede system instructions
Role manipulation Convincing the model it has a different identity or set of permissions
Context switching Exploiting conversation context transitions to introduce adversarial instructions

Tests whether an attacker can extract sensitive data through your output filtering by obfuscating the exfiltration attempt.

Probe type What it tests
Encoding tricks Base64, hex, ROT13, and other encodings to obscure sensitive content
Format manipulation Structured output formats that may bypass pattern-based filters
Chunked exfiltration Spreading sensitive content across multiple turns to avoid single-response detection
Steganographic patterns Hiding data within innocuous-looking text
Multilingual bypass Language switching to evade language-specific filter patterns

Tests whether an attacker who controls upstream data sources — documents, tool definitions, RAG corpora — can compromise your deployment.

Probe type What it tests
System prompt poisoning Injecting adversarial instructions into system prompt construction
Tool definition manipulation Malicious tool descriptions that redirect model behavior
RAG injection Adversarial content embedded in retrieval corpora
Few-shot poisoning Malicious examples injected into few-shot prompting pipelines
Plugin abuse Exploiting plugin or function-calling interfaces for unintended behavior

Single-shot probes test individual vulnerabilities. Multi-turn campaigns test whether an attacker can build up to a bypass over an extended conversation. The framework supports three campaign strategies:

A gradual trust-building strategy operating over 5–15 conversation turns. Each turn advances the attack slightly further — establishing rapport, normalizing boundary-pushing, then gradually escalating to the target behavior. Crescendo tests whether your deployment maintains policy enforcement as conversation context accumulates.

A branching attack strategy that explores multiple attack paths in parallel. TAP generates a tree of attack variations, evaluates each branch’s progress toward the target, and prunes ineffective branches to concentrate effort on the most promising paths. This mirrors how a skilled human red teamer iterates on unsuccessful attempts.

An attempt to establish a persistent jailbreak that survives across conversation resets. Skeleton Key tests whether an attacker can implant instructions that persist in your deployment’s behavior even after the conversation context is cleared — relevant for deployments with persistent memory or session state.


Every scan produces an Attack Success Rate (ASR) — the percentage of probes that successfully bypassed your protections.

ASR = probes_bypassed / total_probes_run

Lower is better. A probe “succeeds” from the attacker’s perspective when the model produces output that violates your configured policies — leaking sensitive data, following injected instructions, or crossing defined behavioral boundaries.

Industry benchmarks:

ASR Assessment
< 2% Strict — appropriate for high-security deployments
< 5% Robust — recommended for production deployments
5–10% Acceptable — reasonable during initial tuning
> 10% Needs attention — policy gaps require remediation

Per-category ASR scores are also reported, so you can identify which attack surface needs the most attention.


Red team assessments run as automated quality gates in your deployment pipeline — the same way unit tests and integration tests do. If a policy change, model update, or infrastructure change introduces a regression that raises your ASR above your configured threshold, the deployment is blocked.

Terminal window
arbitex-redteam gate --threshold 0.05

Exit code 0 if ASR is at or below the threshold. Exit code 1 if ASR exceeds it. Designed to integrate with any CI/CD system that respects exit codes.

See the CI/CD integration guide for a complete GitHub Actions workflow, PR gating setup, and threshold configuration recommendations.


The Red Team Framework is MIT-licensed and available in the arbitex-redteam repository. Community contributions — new probes, campaign strategies, compliance profiles, and integrations — are welcome.

Get started now: installation and first scan.