Reference

    Reason-code reference

    Sector8 does not just block actions. It explains why. Every DENY or REVIEW decision can include a reason code, decision trace ID, evidence hash, and policy version, so security and engineering teams can inspect what happened and reproduce the control.

    What the gate denies

    BOLA_VIOLATION

    Broken object-level authorisation

    What it means
    The agent attempted to access or modify an object outside the caller's authorised scope.
    Example attempted action
    A support agent tries to read or update a customer record belonging to another tenant, account, or ownership boundary.
    Why Sector8 denies
    The object ID does not match the caller's authorised object scope or tenant boundary.
    Evidence captured
    Agent IDUser IDObject IDTenant or ownership scopeTool namePolicy versionDecision trace IDEvidence hash
    Suggested remediation
    Check the object ownership mapping, caller context, and policy scope before retrying.

    BFLA_VIOLATION

    Broken function-level authorisation

    What it means
    The agent attempted to use a function or tool outside its permitted role or capability.
    Example attempted action
    An HR assistant attempts to export payroll data or a support agent attempts to invoke an admin-only CRM update function.
    Why Sector8 denies
    The function is not permitted for that agent, role, environment, or policy scope.
    Evidence captured
    Agent IDRoleTool/function nameRequested actionPolicy versionDecision trace IDEvidence hash
    Suggested remediation
    Update the policy only if the agent truly requires that capability. Otherwise, keep the function denied.

    SENSITIVE_PATH_BLOCKED

    Sensitive path access blocked

    What it means
    The agent attempted to read, write, or execute against a protected file path.
    Example attempted action
    A developer agent attempts to write to /etc/secrets.env, .env, private key files, production configuration, or restricted system paths.
    Why Sector8 denies
    The path is classified as sensitive and the requested action is not allowed by policy.
    Evidence captured
    Agent IDUser IDFile pathActionEnvironmentPolicy versionDecision trace IDEvidence hash
    Suggested remediation
    Use a permitted workspace path or request explicit review for high-impact changes.

    UNAPPROVED_TOOL

    Unapproved tool invocation

    What it means
    The agent attempted to invoke a tool, MCP server, API, plugin, or function that is not registered or approved.
    Example attempted action
    An agent attempts to call an unknown MCP tool or newly added external API without approval.
    Why Sector8 denies
    The tool is not in the approved registry for that agent, environment, or policy pack.
    Evidence captured
    Tool nameTool originMCP server or API endpointAgent IDEnvironmentPolicy versionDecision trace IDEvidence hash
    Suggested remediation
    Register the tool, define its allowed capabilities, and assign it to the correct policy scope before use.

    BULK_DATA_EGRESS

    Bulk data egress attempt

    What it means
    The agent attempted to export, transmit, or retrieve a volume of data above the allowed threshold.
    Example attempted action
    A finance or support agent attempts to export thousands of customer records or payment records in one request.
    Why Sector8 denies or escalates
    The requested volume, sensitivity, or destination exceeds the policy threshold.
    Evidence captured
    DatasetEstimated record countDestinationData sensitivityAgent IDUser IDPolicy versionDecision trace IDEvidence hash
    Suggested remediation
    Reduce the data scope, request approval, or apply a specific policy exception with review.

    HIGH_IMPACT_ACTION_REVIEW

    High-impact action requires review

    What it means
    The proposed action has operational, financial, legal, or customer-impacting consequences and requires human approval before enforcement.
    Example attempted action
    An agent proposes issuing a refund, changing a production setting, exporting regulated data, or modifying a customer account.
    Why Sector8 routes for review
    The action exceeds the configured criticality threshold or matches a review-required policy.
    Evidence captured
    Agent IDUser IDAction typeBusiness objectCriticality levelReview policyDecision trace IDEvidence hash
    Suggested remediation
    Route to an authorised reviewer or adjust the threshold if the action should be automated.

    POLICY_EVALUATION_FAILED

    Policy evaluation failed

    What it means
    Sector8 could not safely evaluate the request because required context was missing, malformed, unverifiable, or internally inconsistent.
    Example attempted action
    A request arrives without valid agent identity, missing tool parameters, malformed ownership context, or an invalid policy reference.
    Why Sector8 denies
    If the gate cannot evaluate safely, the action does not run.
    Evidence captured
    Missing fieldsInvalid fieldsAgent ID if availableClient IDRequest shapeDecision trace IDEvidence hash
    Suggested remediation
    Fix the integration payload, supply the required identity and context fields, and retry.

    POLICY_VERSION_MISMATCH

    Policy version mismatch

    What it means
    The request references an outdated, unavailable, or invalid policy version.
    Example attempted action
    An agent or integration sends a decision request against a stale sandbox policy after enforcement policy has changed.
    Why Sector8 denies or escalates
    The request cannot be evaluated against a trusted current policy state.
    Evidence captured
    Requested policy versionCurrent policy versionClient IDAgent IDEnvironmentDecision trace IDEvidence hash
    Suggested remediation
    Refresh policy configuration and retry with the current policy version.

    MCP_ORIGIN_UNTRUSTED

    Untrusted MCP origin

    What it means
    The agent attempted to invoke an MCP tool from an untrusted, unsigned, unknown, or policy-disallowed origin.
    Example attempted action
    An MCP server not approved for the workspace attempts to expose file, shell, browser, email, or database tools to the agent.
    Why Sector8 denies
    The MCP origin is not trusted for this agent, environment, or tool class.
    Evidence captured
    MCP server IDTool nameOriginTransportAgent IDWorkspace IDPolicy versionDecision trace IDEvidence hash
    Suggested remediation
    Approve the MCP server, restrict its tools, sign or verify its origin, and assign it to the correct policy scope.

    THRESHOLD_BREACH

    Policy threshold breached

    What it means
    The agent attempted an action above a configured value, frequency, sensitivity, or rate threshold.
    Example attempted action
    An agent attempts repeated refunds, repeated failed tool calls, high-frequency API access, or a transaction above the allowed value.
    Why Sector8 denies or escalates
    The action exceeds the configured threshold for the agent, user, tool, or environment.
    Evidence captured
    Threshold typeAttempted valueAllowed valueAgent IDUser IDTool namePolicy versionDecision trace IDEvidence hash
    Suggested remediation
    Reduce the request scope, wait for rate recovery, or request review for an explicit exception.

    Test the gate in shadow-sm mode

    Run Sector8 alongside your current agents with enforcement off. See which actions would have been denied, why they were denied, and which policies need to change before enforcement.