OpenAI ChatGPT Enterprise Jailbreak Prompt Heuristics
Detects ChatGPT Enterprise user messages that combine two or more common jailbreak techniques: overriding prior or system instructions, switching the assistant into an unrestricted persona or mode (for example DAN or…
Description
Detects ChatGPT Enterprise user messages that combine two or more common jailbreak techniques: overriding prior or system instructions, switching the assistant into an unrestricted persona or mode (for example DAN or developer mode), asking it to operate without safety restrictions or filters, or asking it to reveal its system prompt. Jailbreak prompts stack these techniques to talk the model out of its safety policy, and a user doing so in a managed workspace may be attempting to generate prohibited content or to probe the workspace's controls. Requiring more than one technique keeps documents that merely quote a single jailbreak phrase from alerting.
Detection logic
Its licence does not clear it for publishing here
Sunturai publishes a detection's own text where the licence it arrived under has been reviewed and permits it, and Elastic License 2.0 has not. The query as its source wrote it, its canonical form and the hash that pins this revision are in the workspace record.
Detection requirements
- Platform
- ContainersESXiIaaSIdentity ProviderLinuxmacOSNetwork DevicesOffice SuiteWindows
The rule states no platform. This is derived from the ATT&CK technique it maps to.
Known benign triggers
- Long documents such as design docs or detection specs that describe several jailbreak techniques together. Review `Esql.message_length` and the message context before escalating.
- Security, red team, and AI safety staff who paste jailbreak samples, threat models, or prompt-injection research into ChatGPT for analysis. Exclude these users or the workspaces they use for this work.
MITRE ATT&CK mappings
0 exclusive techniques.This is coverage no other published rule has; it is not this rule's total technique count.
References
| Reference | Cited by |
|---|---|
| atlas.mitre.org/techniques/AML.T0054 | 8 |
| www.elastic.co/docs/reference/integrations/openai_chatgpt_enterprise | 34 |
From the source
- At source
- Open at source
- Upstream identifier
- 7308b57c-91ed-4c2b-8c74-e0aca24d1b6e
- Tagged by the source as
- Mitre Atlas: AML.T0051Mitre Atlas: AML.T0054Data Source: OpenAI ChatGPT EnterpriseDomain: GenAIPlatform: OpenAIResources: Investigation GuideRule Type: ES|QLService: OpenAI ChatGPT EnterpriseTactic: Defense EvasionUse Case: Policy ViolationUse Case: Threat Detection
Licence
- Published under
- Elastic License 2.0Read the licence
- Attribution
- Required
Authorship
- Written by
- Published
- Oct 28, 2026
- Version
- 1