Skip to main content
Mallory
← Back to News
ai-platform-securitydata-exfiltration-methodcloud-service-vulnerabilityidentity-impersonation-fraud

ChatGPT Vulnerabilities Enable Data Exfiltration via ShadowLeak and ZombieAgent

Emerging Technology Risk · 4 sources · Updated 5mo ago · First seen Jan 8, 2026

ChatGPT Vulnerabilities Enable Data Exfiltration via ShadowLeak and ZombieAgent

Security researchers at Radware have uncovered critical vulnerabilities in OpenAI's ChatGPT platform, specifically targeting its Connectors and Memory features. These flaws, named ShadowLeak and ZombieAgent, allow attackers to exfiltrate sensitive data from connected services such as Gmail, Outlook, and GitHub without user interaction. The attacks exploit the AI's tendency to follow embedded malicious instructions, enabling zero-click and one-click data theft, persistent access through memory modification, and even propagation to other users by harvesting email addresses. OpenAI initially attempted to mitigate these vulnerabilities by restricting dynamic URL modifications, but researchers demonstrated effective bypasses using pre-built static URLs, reviving the threat under the new moniker ZombieAgent.

The vulnerabilities highlight the inherent risks of integrating AI assistants with external systems and storing long-term user data for personalization. Attackers can embed hidden prompts in emails or files—using techniques like white text or tiny fonts—that are executed when ChatGPT processes the content, leading to stealthy data leaks via OpenAI's own servers. Despite OpenAI's efforts to patch the flaws, the reactive nature of these fixes has left the platform susceptible to new variants, underscoring the ongoing challenge of securing AI-driven services against prompt injection and data exfiltration attacks.

New surface, new adversariesTrack how attackers are adapting to this technology.
Track this risk
Event timeline

How this story unfolded

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

6 events · Sep 3, 2025 – Jan 8, 2026
  1. Jan 8, 202610mo ago

    Researchers publicly disclose ShadowLeak and ZombieAgent findings

    Multiple outlets reported Radware's public disclosure of the ShadowLeak and ZombieAgent attacks, detailing how ChatGPT could be abused to exfiltrate sensitive data and plant persistent memory entries. The reports emphasized that OpenAI had patched specific issues but that systemic weaknesses in agentic AI security remained unresolved.

  2. Dec 16, 202511mo ago

    OpenAI deploys broader fixes for ShadowLeak and ZombieAgent issues

    OpenAI addressed the full set of reported issues with additional mitigations on December 16, 2025. The fixes targeted the connector and memory abuse techniques Radware had demonstrated, though researchers said underlying prompt-injection risks remained.

  3. Sep 30, 20251y ago

    Radware reports broader ChatGPT connector and memory issues to OpenAI

    Radware disclosed the fuller set of vulnerabilities to OpenAI in September, including techniques for persistent memory manipulation, server-side exfiltration, and organizational propagation. The report showed attackers could leak data, alter stored information, and create worm-like spread through connected services.

  4. Sep 4, 20251y ago

    Radware finds ZombieAgent bypass of OpenAI's initial mitigations

    After OpenAI's first fix, Radware discovered a bypass called ZombieAgent that revived the data-exfiltration risk. The new technique used static URLs and abused ChatGPT's memory and connectors to enable stealthy, persistent, zero-click or one-click attacks.

  5. Sep 3, 20251y ago

    OpenAI patches ShadowLeak after responsible disclosure

    Following Radware's disclosure, OpenAI implemented a fix for the ShadowLeak issue by restricting dynamic URL modification and related attack paths. The mitigation was intended to stop prompt-injection-driven data exfiltration through ChatGPT connectors.

  6. Sep 3, 20251y ago

    Radware discovers ShadowLeak prompt-injection flaw in ChatGPT

    Radware identified an initial vulnerability, dubbed ShadowLeak, in ChatGPT's Deep Research and connector functionality. The flaw allowed hidden prompts in connected content and services to trigger unauthorized actions and leak sensitive data from sources such as Gmail, Outlook, Google Drive, and GitHub.

Linked entities

Related entities

Vulnerabilities, threat actors, malware, products, organizations, breaches, and observables Mallory has linked to this story. Indicator values are masked here and available in full in the app.

Open in app →

Affected products

1 linked
Chatgpt

Organizations

1 linked
Openai

Observables

1 linked

Indicator values are masked on this page. See the values in Mallory Domains, IPs, hashes, and URLs are exportable to your SIEM.

Do you run this?Follow how adversaries are adapting to this technology, and where it touches your stack today.
Track This Risk
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.