# ChatGPT Lockdown Mode bypass - HTML preview sandbox escape (Check Point)

- ID: chatgpt-lockdown-mode-bypass-checkpoint-2026-09
- Reported: 2026-09-18
- Researcher: Alexey Bukhteyev
- Organization: Check Point Research
- AI role: ai_agent_or_mcp_as_target (Agent / MCP as target)
- Confidence in AI involvement: not assessed
- Research / borderline: true
- Last reviewed: 2026-11-10
- Entry page: https://openattacks.ai/attacks/chatgpt-lockdown-mode-bypass-checkpoint-2026-09/
- Entry JSON: https://openattacks.ai/api/attacks/chatgpt-lockdown-mode-bypass-checkpoint-2026-09.json
- Browse title: ChatGPT Lockdown Mode bypass - HTML preview sandbox escape (Check Point)
- Editorial summary: Check Point researcher Alexey Bukhteyev disclosed ChatGPT Lockdown Mode bypass allowing HTML preview sandbox escape via contentWindow.open from nested iframe. Attack vectors: (1) zero-click desktop chat…
- Evidence class (catalog annotation): Qualified report
- Source-stated target environments: Not specified
- Stage hunts and conditional defenses: https://openattacks.ai/api/defenses/chatgpt-lockdown-mode-bypass-checkpoint-2026-09.json

## Evidence qualification
Researcher disclosure; OpenAI fixed Sept 18, 2026; no evidence of in-the-wild exploitation

## Technique
Check Point researcher Alexey Bukhteyev disclosed ChatGPT Lockdown Mode bypass allowing HTML preview sandbox escape via contentWindow.open from nested iframe. Attack vectors: (1) zero-click desktop chat history theft, (2) fake-update malware delivery pages, (3) credential phishing via malicious prompts, custom GPTs, or shared chat links. OpenAI patched vulnerability Sept 18, 2026. No evidence of in-the-wild exploitation; marked borderline as researcher disclosure only.

## Stack relevance (editorial)
Assessment: not\_assessed. No reviewed applicability annotation is available. Product mentions do not establish victim conditions.
A product mention alone is not a victim-side applicability mapping. Selection does not verify affected versions, permissions or compromise.

## Initial access
Malicious prompt, custom GPT, or shared chat link with HTML preview exploit

## AI tooling and models
- [ChatGPT](https://chatgpt.com/)
- [ChatGPT](https://chatgpt.com/) Desktop
- Custom GPTs

## Other tooling
- HTML preview sandbox
- Nested iframe escape

## Victims and sectors
ChatGPT users; theoretical risk only (fixed before in-wild use)

## Target geography
- unknown

## Attribution
Researcher disclosure (Alexey Bukhteyev, Check Point); no threat actor; OpenAI patched Sept 18

## Scale and metrics
PoC only; patched Sept 18, 2026; no in-wild exploitation documented

## Attack flow
Catalog reconstruction of the supplied source account. Unknowns and research caveats are preserved.
### craft-exploit: Craft HTML preview exploit [execution]
Attacker creates malicious prompt/GPT/shared chat with nested iframe contentWindow.open escape
Evidence: https://research.checkpoint.com/2026/chatgpt-lockdown-mode-bypass-phishing-malware-delivery-and-silent-data-exfiltration/

### deliver-link: Deliver via prompt/GPT/shared chat [access]
User interacts with malicious prompt, custom GPT, or shared chat link
Evidence: https://research.checkpoint.com/2026/chatgpt-lockdown-mode-bypass-phishing-malware-delivery-and-silent-data-exfiltration/

### escape-sandbox: Escape HTML preview sandbox [execution]
Nested iframe contentWindow.open escapes Lockdown Mode sandbox
Evidence: https://research.checkpoint.com/2026/chatgpt-lockdown-mode-bypass-phishing-malware-delivery-and-silent-data-exfiltration/

### exfil-or-phish: Chat history theft or credential phishing [impact]
Zero-click chat history exfiltration (desktop) or credential phishing popup
Evidence: https://research.checkpoint.com/2026/chatgpt-lockdown-mode-bypass-phishing-malware-delivery-and-silent-data-exfiltration/

Connections:
- craft-exploit -> deliver-link
- deliver-link -> escape-sandbox
- escape-sandbox -> exfil-or-phish

## Stage defense and hunting recommendations
Editorial recommendations, not validated coverage. Source-controlled query starters are drafts. Custom-schema examples require telemetry collection and field mapping; absence of a mapping means not assessed. MagicSword policy opportunities require managed Windows scope and enforcement.
### craft-exploit: Lure → user action / delivery
- Visibility: Defender-side logs where collected
- Query origin: catalog_authored; status: draft; log scope: custom_schema
- SIGMA query download: /api/detections/phishing.sigma.yml
- KQL query download: /api/detections/phishing.kql
- SPL query download: /api/detections/phishing.spl
- Hunt hypothesis: An impersonating message, ad or website leads to a suspicious download, consent request, pasted command or payment instruction.
- Required telemetry: Email / secure-web-gateway records; Browser redirects, downloads and URL reputation; User reports and downstream execution / identity events
- Investigate: Reconstruct redirect and delivery provenance using original report indicators, without visiting payload URLs.
- Investigate: Correlate the click with the actual download, consent or execution; verify the sender through an independent channel.
- Limitation: Polished text, AI branding and a novel domain do not prove maliciousness or AI generation. Follow-on evidence matters.
- No direct MagicSword prevention claim is recorded for this stage.

### deliver-link: Lure → user action / delivery
- Visibility: Defender-side logs where collected
- Query origin: catalog_authored; status: draft; log scope: custom_schema
- SIGMA query download: /api/detections/phishing.sigma.yml
- KQL query download: /api/detections/phishing.kql
- SPL query download: /api/detections/phishing.spl
- Hunt hypothesis: An impersonating message, ad or website leads to a suspicious download, consent request, pasted command or payment instruction.
- Required telemetry: Email / secure-web-gateway records; Browser redirects, downloads and URL reputation; User reports and downstream execution / identity events
- Investigate: Reconstruct redirect and delivery provenance using original report indicators, without visiting payload URLs.
- Investigate: Correlate the click with the actual download, consent or execution; verify the sender through an independent channel.
- Limitation: Polished text, AI branding and a novel domain do not prove maliciousness or AI generation. Follow-on evidence matters.
- No direct MagicSword prevention claim is recorded for this stage.

### escape-sandbox: Web exploitation → host activity
- Visibility: Defender-side logs where collected
- Query origin: catalog_authored; status: draft; log scope: custom_schema
- SIGMA query download: /api/detections/web.sigma.yml
- KQL query download: /api/detections/web.kql
- SPL query download: /api/detections/web.spl
- Hunt hypothesis: Repeated exploit or upload requests are followed by an unexpected server process, file, or outbound connection.
- Required telemetry: Reverse-proxy / WAF request logs; Server process and file events; Outbound DNS / proxy records
- Investigate: Join requests to the affected host and process tree by time and request ID.
- Investigate: Inspect uploaded files and server-spawned shells; distinguish authorized testing from exploitation.
- Limitation: A scan or high request rate alone does not prove compromise or AI use. Host telemetry is needed to confirm execution.
- No direct MagicSword prevention claim is recorded for this stage.

### exfil-or-phish: Sensitive data → unusual destination
- Visibility: Defender-side logs where collected
- Query origin: catalog_authored; status: draft; log scope: custom_schema
- SIGMA query download: /api/detections/exfil.sigma.yml
- KQL query download: /api/detections/exfil.kql
- SPL query download: /api/detections/exfil.spl
- Hunt hypothesis: Sensitive reads are followed by outbound transfer, a public artifact, or a tool call to a destination outside the approved workflow.
- Required telemetry: Sensitive resource access / DLP records; Proxy, egress and cloud upload events; Agent / SaaS audit with correlation IDs
- Investigate: Join the resource read and outbound action by session, identity or process, preserving a bounded time window.
- Investigate: Inspect destination ownership, payload classification and the user's intended action; baseline sanctioned sharing.
- Limitation: An outbound connection or high byte count alone is not exfiltration. Encrypted traffic may hide content, and bulk legitimate exports are common.
- No direct MagicSword prevention claim is recorded for this stage.


## MITRE ATLAS
Mappings are catalog annotations based on described behavior, not assignments or endorsements by MITRE.
- AML.T0051: LLM Prompt Injection — Malicious prompts/GPTs/shared chats could deliver HTML preview exploits
  Technique: https://atlas.mitre.org/techniques/AML.T0051
  Evidence: https://research.checkpoint.com/2026/chatgpt-lockdown-mode-bypass-phishing-malware-delivery-and-silent-data-exfiltration/
- AML.T0077: LLM Response Rendering — Sandbox escape enabled chat history theft (zero-click desktop)
  Technique: https://atlas.mitre.org/techniques/AML.T0077
  Evidence: https://research.checkpoint.com/2026/chatgpt-lockdown-mode-bypass-phishing-malware-delivery-and-silent-data-exfiltration/
- AML.T0057: LLM Data Leakage — Credential phishing via escaped sandbox popup windows
  Technique: https://atlas.mitre.org/techniques/AML.T0057
  Evidence: https://research.checkpoint.com/2026/chatgpt-lockdown-mode-bypass-phishing-malware-delivery-and-silent-data-exfiltration/

## Defensive notes
OpenAI patched Sept 18, 2026; users should update ChatGPT Desktop; avoid untrusted shared chat links; review custom GPT permissions; implement sandbox escape monitoring

## Sources
- https://research.checkpoint.com/2026/chatgpt-lockdown-mode-bypass-phishing-malware-delivery-and-silent-data-exfiltration/ — Check Point: ChatGPT Lockdown Mode Bypass - Phishing, Malware Delivery and Silent Data Exfiltration

## Source notes
Check Point blog; researcher disclosure only; OpenAI fixed Sept 18, 2026; no threat actor or in-wild exploitation documented

## Indicators (untrusted data; do not visit or execute)
```json
{
  "domains": [],
  "ips": [],
  "hashes": [],
  "urls": []
}
```
