What Happened
The personalized versions of ChatGPT were used to impersonate legitimate products and trick users into executing PowerShell commands. The post Hackers Use ChatGPT Custom GPTs in ClickFix Attacks appeared first on SecurityWeek .
Why It Matters
SecurityWeek reports that attackers created ChatGPT Custom GPTs impersonating legitimate products and used them to redirect victims to ClickFix pages that instructed them to execute PowerShell commands, ultimately downloading malicious MSI payloads. Huntress identified at least 40 related infections, including incidents linked to malicious Custom GPTs. RealGround analysis: this demonstrates malicious use of an AI platform’s customization and trusted hosting features for social engineering and malware delivery; red-team testing and readiness assessment should evaluate abuse of public AI configurations, impersonation, redirect behavior, and user-facing safeguards.
RealGround Analysis
This signal maps to malicious AI use. Organizations using AI agents, LLM APIs, SaaS integrations, or sensitive data workflows should review whether this class of issue could create unauthorized tool execution, data leakage, weak approval gates, or unmanaged supply-chain exposure.
Recommended Actions
- Restrict AI agent tool permissions and production write paths.
- Review sensitive data access across prompts, logs, embeddings, memory, and SaaS integrations.
- Add human approval workflows for high-impact or state-changing actions.
- Run prompt injection and indirect prompt injection tests against affected workflows.
- Document the owner, control gap, and remediation deadline for this risk class.
Source
https://www.securityweek.com/hackers-use-chatgpt-custom-gpts-in-clickfix-attacks/