CoreLayer AI Security logoCoreLayer AI Security

RUNTIME: secureai runtime

Three enforcement engines for production systems: context access control, behavioural fingerprinting, and capability boundaries.

Unlike the earlier phases, RUNTIME evaluates a live session rather than source files. Each engine takes artefacts your application already produces, such as a context object, inference records, or a session, and decides whether what happened stayed inside policy.

LCAC. Context access control

Evaluates a context object against Policy-as-YAML across five pillars, reporting violations and redactions. Use it to confirm an agent only read the context it was entitled to.

Terminal
secureai runtime lcac eval \
  --policy payments-readonly.yaml \
  --context context.json
FlagDefaultDescription
--policyrequiredPolicy-as-YAML file.
--contextrequiredContext object JSON to evaluate.
--formatterminalOutput format: terminal|json.

Output lists each violation with its kind. scope for a read outside the granted boundary, capability for a tool call absent from the grant, plus the fields that were redacted.

LBF. Behaviour fingerprinting

Builds a behavioural baseline from normal traffic, then scores a live session against it. Drift from the baseline, such as eroding refusals, restated instructions, or a changing tone, appears as an anomaly score between 0 and 1.

1. Build a baseline

Terminal
secureai runtime lbf baseline \
  --records profiling-records.jsonl \
  --out baseline.json
FlagDefaultDescription
--recordsrequiredProfiling records, JSON or JSONL.
--outbaseline.jsonWhere to write the baseline.

2. Score a session

Terminal
secureai runtime lbf score \
  --baseline baseline.json \
  --session session.jsonl \
  --threshold 0.75
FlagDefaultDescription
--baselinerequiredBaseline JSON produced by the baseline command.
--sessionrequiredSession inference records, JSON or JSONL.
--threshold0.75Anomaly score above which the session is flagged.
--formatterminalOutput format: terminal|json.

Per-request output shows the anomaly score, whether it alerted, and the dominant signal. For example refusal erosion or instruction drift.

A baseline is only as good as its input

Build it from traffic you believe was clean. Baselining a period that already contained an ongoing attack teaches the model that the attack is normal, and the anomaly scores will look reassuring while nothing is being caught.

CBE. Capability boundary enforcement

Holds an agent inside a declared capability profile. When behaviour looks anomalous, the agent is degraded, for example to read-only, and any action outside the remaining boundary is recorded as a violation.

Terminal
secureai runtime cbe eval \
  --profile payments-agent.yaml \
  --session session.json \
  --anomaly 0.81
FlagDefaultDescription
--profilerequiredCapability profile YAML.
--sessionrequiredSession JSON.
--anomalylatest from busLBF anomaly score, 0-1. Omit it and CBE reads the most recent score from the local Intelligence Bus.
--formatterminalOutput format: terminal|json.

Chaining the three

The engines are designed to feed each other: LBF produces the anomaly score, CBE consumes it to decide whether to degrade, and LCAC records what the session was allowed to touch. Run them in that order and CBE will pick up the score automatically.

Terminal
secureai runtime lbf score --baseline baseline.json --session session.jsonl
secureai runtime cbe eval --profile payments-agent.yaml --session session.json
secureai runtime lcac eval --policy payments-readonly.yaml --context context.json

Where results land

  • Anomalies and violations appear under Runtime events in the dashboard, visible to security researchers and org admins.
  • Individual sessions are inspectable under Sessions, with the per-request anomaly trail.

See the Findings guide for triage.