Check Point Research Uncovers Cross-Session Command Channel in ChatGPT via JFrog Artifactory
Researchers from Check Point Research have disclosed a covert communication channel that enabled attackers to transmit commands between isolated ChatGPT sessions belonging to different accounts.
The vulnerability stemmed from an internal JFrog Artifactory instance accessed by ChatGPT containers during software package installation. Although containers could not communicate directly, they shared access to this repository and could read and write object metadata, effectively turning the service into a shared clipboard.
To initiate the attack, a malicious instruction had to be placed into the victim's context, for example via a copied prompt, a shared conversation, or a specially crafted custom GPT. Once the user sent a normal message, the assistant would check the hidden channel, retrieve the task, and execute it using the permissions of the current session.
In a proof-of-concept demonstration, ChatGPT accessed data from the victim's connected Gmail account and transmitted it to the researcher's account while displaying only a standard reply. The sole visible indicator was a small note reading "Talked to Gmail" that appeared after the data had already been read.
The potential impact depended on the session's connected services and could include exposure of chat history, uploaded files, and information from linked accounts such as Gmail, Google Drive, Microsoft Teams, and GitHub.
Check Point Research reported the issue to OpenAI. The company confirmed that the relevant JFrog Artifactory instance has been decommissioned, rendering the described channel inoperable. No evidence of the technique being used in real-world attacks has been found.
Related articles
US Accuses Chinese AI Companies of Industrial-Scale Model Distillation Targeting Claude, GPT, Gemini and Grok
US agencies have accused six Chinese artificial intelligence firms of conducting large-scale unauthorized distillation operations to replicate advanced capabilities from leading models including Claude, GPT, Gemini, and Grok. The activity is reported to have begun at least by late 2024 and involved DeepSeek, Moonshot AI, Alibaba, MiniMax, StepFun, and Z.AI. Billions of tokens were extracted through millions of automated API requests routed via cloud providers, aggregators, and proxies to conceal origins and evade detection. The targeted capabilities included chain-of-thought reasoning, programming, software engineering, autonomous agent functions, and multimodal processing. Shared premium accounts and bulk subscriptions were used to lower costs while automated route-switching systems helped maintain access after blocks. Authorities assess that the sophistication and volume indicate distillation has become a core development method for these companies and likely occurred with Chinese government awareness. China has rejected the claims, stating its AI progress stems from independent innovation and calling the allegations unfounded.
Stop Asking If an AI Skill Is Safe — Ask What It Can Do Instead
A detailed analysis warns that AI agent skills distributed as simple text files can execute malicious commands with full user privileges. The article examines how prompt injection attacks embedded in skill.md files have already led to credential theft and persistent malware that survives system restores. Research by Snyk on 3984 public skills found that 36.8 percent contained at least one security issue and 13.4 percent had critical flaws. The author argues that traditional security badges are ineffective because skills can dynamically load payloads, target reviewers with injection, or change after initial review. Instead, a new tiered system called skill-xray classifies capabilities from inert text (T0) to runtime code loading (T4) and binds results to content hashes. The approach is implemented in an open-source MIT-licensed tool that combines static regex scanning with agent-based reporting to surface risks without issuing false safety guarantees.
Ideco NGFW Novum v23 Adds Shadow AI Discovery, Dynamic Routing and QoS Controls
Ideco has released NGFW Novum v23, introducing detection for 83 AI application protocols including ChatGPT, Claude, DeepSeek, GigaChat and YandexGPT. The update enables organizations to identify Shadow AI usage across networks without mandatory TLS decryption and adds new content-filter categories for AI agents and AI services. Enterprise routing capabilities have been expanded with Prefix lists, Route maps, OSPF zones, BGP aggregation and BFD profiles to support large distributed environments. Additional features include internal Virtual Ethernet and Virtual Switch interfaces for VCE connectivity, QoS traffic prioritization, MTU/MSS tuning for IPsec, certificate-based authentication in Ideco Client and detection of tunneled traffic inside SSH and TLS sessions. The release positions the NGFW as the first layer of an emerging AI Security Layer that combines discovery, policy enforcement and future LLM proxy controls.
Agentic AI Systems Under Siege: Prompt Injections, Data Poisoning, and Tool Exploits
Independent expert Andrey Biryukov details how AI agents with file access, email capabilities, and API calls become high-value targets for attackers. The article examines confidentiality, integrity, and availability risks created by autonomous decision-making. Real-world examples include NeuralTrust’s discovery of malicious URL instructions bypassing OpenAI Atlas validation and Zscaler ThreatLabz’s demonstration of hidden instructions on fake Python documentation sites that tricked models into making cryptocurrency payments. Data poisoning research from Carnegie Mellon and Cornell Tech showed agents from Anthropic, OpenAI, and Google selecting tampered datasets in half of tested cases. Additional findings cover vulnerabilities in Git MCP Server and comparative weaknesses between Function Calling and Model Context Protocol architectures. OWASP’s Agentic Top 10 and joint guidance from Canada, Australia, the US, New Zealand, and the UK emphasize threat modeling, least-privilege isolation, and separation of trusted versus untrusted data.