OpenAIAI
LowCapability
OpenAI Enhances ChatGPT Agents with Prompt Injection Defenses
AI Impact Summary
OpenAI has implemented defenses against prompt injection and social engineering attacks within ChatGPT agents. This involves restricting potentially risky actions and safeguarding sensitive data within agent workflows, enhancing the overall security and reliability of AI agents. This capability allows developers to build more robust and trustworthy AI applications.
OpenAI Enhances ChatGPT Agents with Prompt Injection Defenses
Affected Systems
ChatGPT
Business Impact
Improved security and reliability of ChatGPT agents reduces the risk of misuse and data breaches.
Models affected
- Date
- Date not specified
- Change type
- capability
- Severity
- low