POL-010 · All channels
Jailbreak detection
Compiled into the runtime gateway and evaluated inline on every prompt, tool call and completion in scope. Owned by Red Team.
Triggers / 30d
59
blocks, masks and escalations
Integrations bound
0
enforced at each connection
Severity
high
owner Red Team
Added latency
7 ms
p99 within the 60 ms budget
Rule definition
Compiled expression
When
- known jailbreak signature
- role-play override attempt
Then
- block
- open security case
Policy as code
apiVersion: truint.ai/v1
kind: RuntimePolicy
metadata:
id: POL-010
name: "Jailbreak detection"
owner: "Red Team"
scope: "All channels"
spec:
severity: high
mode: enforce
when:
- "known jailbreak signature"
- "role-play override attempt"
then:
- "block"
- "open security case"Governance metadata
- Policy ID
- POL-010
- Owner
- Red Team
- Scope
- All channels
- State
- Enforcing inline
- Catalog version
- 2026.07.3
- Last change
- 2026-07-22 · approved by AI Council
Bound integrations
Where this rule executes
Applies estate-wide rather than to a specific connection.
Recent evaluations
Decisions where this rule fired
No evaluations from this rule in the current buffer.