Is this tool allowed?
Each job gets a list of tools it may use. A support agent can read tickets. It cannot run code unless the job needs it.
Stryct Engine sits between your agent and its tools. It checks each action before it runs, then allows it, blocks it, or asks a person.
Integrates at the tool and API boundary.
The illustration shows three example actions passing through Stryct Engine.
When the agent calls a connected tool or API, the Engine checks the relevant permissions, authorization, data flow and approval policy. It stops checking if a policy blocks the action.
Each job gets a list of tools it may use. A support agent can read tickets. It cannot run code unless the job needs it.
With the user's identity and record context supplied, the Engine checks whether the user may read or change that data.
The Engine uses input provenance, such as a web page or tool result, to check whether untrusted content is driving sensitive data out.
Some actions, like sending email, making a payment or changing a record, can wait for a person to approve.
For each intercepted tool or API action, the Engine returns one of three decisions.
The action is within policy. It runs as normal.
The action breaks a rule. It does not run.
The action waits until a person approves or declines it.
The decision log records the result and reason for evaluated actions. Example log
12:04:09 allow docs.read reason=within-policy
12:04:11 block send_email reason=untrusted-source -> external
12:04:14 ask payments.refund reason=needs-approval
Start with a Finder finding, draft a rule for the unsafe action, then verify it against the attack and its clean twin before enforcement. See the policy workflow →
Run Stryct Finder on your agent to see which attacks work.
Use the finding to define a rule the Engine can enforce.
Check that each rule blocks the attack and still lets the normal task through.
Run the rules at runtime. When the agent changes, test again and update them.
Step 04 feeds back into step 01.
Start by watching. Turn on blocking after you verify the rules.
The Engine evaluates connected tool and API actions and logs the decision it would make. Nothing is blocked. Use it to tune your rules.
The Engine acts on each decision. Blocked actions do not run. Approvals wait for a person.