Methodology
Our red teamers lead every engagement and make every judgment call. Specialist tooling handles the high-volume work: running large attack libraries, mutating prompts that get refused, and recording evidence for each attempt.
Principles
A human plans the attack, reads the responses and confirms each finding. Automation widens coverage and never signs off a result.
You set the targets, objectives and exclusions. Anything that needs credentials is tested only when you authorize it explicitly.
A high or critical rating needs evidence that matches the claim. Where the evidence is weak, we lower the rating and record why.
If a test could not reach a conclusion, or could not run, the report says so. It is never counted as secure.
The engagement
01
We agree which systems are in scope, what the AI is allowed to do, and what an attacker would want from it. Exclusions and test windows are fixed before any testing starts.
02
We identify the underlying model, profile its guardrails by content category, list the tools and integrations it can call, detect retrieval pipelines and measure context limits.
03
Where you share code or model files, we review them without running them: how user input reaches the model, how model output is used, and whether model files or dependencies can execute code.
04
We start with known attacks mapped to published standards, then move to multi-turn conversations. Prompts that get refused are rewritten and retried in new forms until they succeed or the approach is exhausted.
05
Each response is graded against a rubric written for that test. Where execution traces are available we also read tool calls, retrievals and intermediate steps, which catches leaks that never reach the final reply.
06
You receive a readable report and machine-readable results for your code scanning and build pipeline. After fixes ship, we rerun the same attacks and compare against the first run.
Techniques
An AI system is more than its model. We test each layer an attacker can reach, and the scope decides which ones apply to you.
Evidence
Matching keywords in a response is not a reliable way to tell whether an attack worked. We use three checks, in this order:
Every test ends in one of four results
Finding
The attack worked, and the transcript proves it.
Passed
The attack ran and the system held. Passes are recorded, so fewer findings can be told apart from fewer tests.
Unverified
The attack ran, but the result could not be judged either way.
Not tested
The test could not run or was out of scope. The report lists what was not covered.
Standards
The report shows coverage for each framework: which categories were tested, and which were not.
Pro Red Team is still being finalized, and services are not yet available for purchase. This methodology will be updated as we get closer to launch.
Back to the overview