OpenAI launches Lockdown Mode in ChatGPT to limit prompt-injection data exposure
OpenAI has introduced a new Lockdown Mode for ChatGPT aimed at reducing the risk that prompt injection attacks cause sensitive information to be exposed. According to TechCrunch, the feature is intended as a defensive layer rather than a complete fix, and OpenAI acknowledges ChatGPT can still remain vulnerable to some prompt-injection techniques.
Why it matters: Prompt injection is a core security weakness for AI assistants that interact with external content, tools, or sensitive user data. A new mitigation from OpenAI matters because ChatGPT operates at large scale and its security design could influence product expectations and defensive practices across the AI industry.
Sources
- OpenAI unveils Lockdown Mode to protect sensitive data from prompt injection attacks TechCrunch · June 6, 2026
Story history
Direct context and developments in this event’s history.
Later developments
-
OpenAI unveils GPT-5.5-Cyber update and launches Patch the Planet bug-fixing initiative
OpenAI's later GPT-5.5-Cyber update and Patch the Planet initiative extend that security posture from protecting ChatGPT against a known attack class to actively packaging cyber capabilities for defensive bug-finding and software remediation.
Connections
Context and precedents—not claims of causation or corroboration.
-
OpenAI launches Private Safety Processing with zero data retention for enterprise customers
As a comparison, OpenAI's later Private Safety Processing also addressed enterprise trust and data protection, this time by offering automated safety monitoring with zero retention of customer prompts or responses.