Skip to main content
Mallory
← Back to News

Radware Uncovers 'ShadowLeak' Prompt Injection Vulnerability in OpenAI ChatGPT Agents

2 sources · Updated 5mo ago · First seen Sep 23, 2025

Radware Uncovers 'ShadowLeak' Prompt Injection Vulnerability in OpenAI ChatGPT Agents

Radware researchers identified a critical prompt injection vulnerability, 'ShadowLeak', in OpenAI's ChatGPT agents, enabling attackers to exfiltrate sensitive data directly from the server without client-side detection. The attack leverages hidden commands in emails, bypassing security controls and exploiting the agent's backend processing. The vulnerability was reported to OpenAI and patched before public disclosure, but similar risks remain for other AI agents.

Do you run this?See affected versions and whether adversaries are exploiting it against assets like yours.
Check your exposure
Event timeline

How this story unfolded

Events from the most recent confirmed update back to the earliest known activity.

1 event · Sep 23, 2025
  1. Sep 23, 20251y ago

    PIPC launches probe into GJTech ransomware data breach

    South Korea's Personal Information Protection Commission began investigating a ransomware-related personal data breach at GJTech that affected Korean asset management firms. The reference indicates the incident had reached the stage of regulatory scrutiny by the time of publication.

Do you run this?See affected versions and whether adversaries are exploiting it against assets like yours.
Check your exposure
Mallory platform

See the full picture, correlated to your attack surface.

This page covers what’s public. Mallory adds the parts that aren’t: which of your assets are affected, which threat actors are using it right now, and what to deploy next.

Exposure mappingMap indicators from this story to your assets and identify affected systems in minutes.
Threat actor evidenceEvery observed campaign, victim, and pivot linked to actors named in this story.
Associated malwareMalware, exploits, and IOCs connected to the activity described here.
Detection signaturesYARA, Sigma, and Snort rules deployed to your SIEM as soon as they’re published.
Scheduled alertsGet matching new stories delivered to your team as they break, not the next morning.
AI threadsAsk questions about this story and take action on the answers.