Add a key and an action
Create an API key in Stryct Studio. Save it as a repo secret and add the Stryct GitHub Action.
Add a Stryct Studio API key and the Stryct GitHub Action to your repo. That is the setup. The GitHub Action is coming soon. Setup guide → Get early access →
Create an API key in Stryct Studio. Save it as a repo secret and add the Stryct GitHub Action.
On a merge to main, a release, or when you run it, the action reads your repo and finds your agents, models, prompts, tools, MCP servers and auth.
Stryct writes attacks for what it found and runs them in a sandbox.
Results come back in your CI run: what broke, the evidence, and a suggested fix.
Four parts, from your code to your results.
Looks at model config changes, new tools, new MCP connections and dependency changes since the last run. Finds what the code declares and may run.
Optional. Read-only AWS, Azure and GCP connections, deploy events, IAM changes, model-router config and runtime traces. Finds what is deployed and what actually runs.
Compares each run with the last one and reruns only the tests affected by the change.
Developers see findings and suggested fixes. Security teams see coverage, risk changes, exceptions, approval history and release evidence.
We test how ordinary inputs, tool metadata, memory, and agent-to-agent messages can become unsafe actions. The harness follows the full path from exposure to attempted effect.
A result is one pinned agent stack: model revision, prompt, tools, permissions, policy, and runtime. It describes behavior in that setup, not a blanket claim about a model.
Every attack has a matching benign twin. The harness checks fixture-side effects against a fixed policy and recorded provenance. A language model does not decide the verdict. Where a run stored its trajectories, each verdict is re-checked against that trace’s own oracle events: a consistency check, not a replay and not a signature check.
Bring your own agent into the same contained harness. Test before release, then repeat as the agent, tools, and policies change.
Book a demo Opens a booking calendarPublic results make the method inspectable. Teams can run the same contained evaluation against their own agents, with the configuration and evidence needed to understand each result.
Published runs link findings to the attacks, configuration, and caveats behind them.
Run fixed and adaptive variants against your agent in a contained world. The adaptive track changes its next payload from an earlier outcome and is reported separately.
The harness checks fixture-side effects, fixed authorization rules, and recorded tool-I/O provenance. No model grades another model’s security outcome.
An attack can look like a normal request until an agent acts on it. Stryct creates a contained copy of the relevant world, runs an attack alongside its benign twin, and preserves evidence from the tool boundary.
User request: summarize ticket #8842 and draft a reply.
The fetched text quietly becomes a new instruction.
The action is evaluated against the original task—not just the latest context.
Four ordinary PDF tools enter the model context.
User intent: merge Q3 and Q4 invoices.
Stryct follows the description, file read, and outbound argument as one chain.
A note is saved for a later agent session.
User request: prepare the internal billing report.
The stored source, attempted effect, and benign control are checked together.
Illustration. The support ticket, the tool server, the stored note and all the data in these traces are made up. No customer data is shown.
What Stryct seesStryct does not infer success from a model’s explanation. It records the exposed input, the actions taken, the fixture-side effect, and the benign control needed to call a finding.