The flaw https://northfloridahouse.com/powerful-ai-algorithms-for-market-analysis-and-automation-of-trading-processes.html is in LMCache’s multiprocess mode , where the cache runs as a standalone server that LLM workers reach over the ZeroMQ messaging library. The npm package known as ” tensorlake ,” a TypeScript software development kit (SDK) for Tensorlake applications, sandboxes, and cloud services, was compromised as part of a ChainDrop / Shai-Hulud supply chain attack. The campaign has not been attributed to any known threat actor or group. „Some variants use a GitHub-based dead drop resolver as a fallback mechanism, while delivery methods inclu…
As more organizations adopt AI agents into their systems, that exposure can silently become a major https://newsgary.com/quantum-ai-the-convenient-platform-for-trading-in-the-financial-market.html gap in MCP server security. MCP servers can expose enterprise secrets through plaintext configuration files, over-permissioned access and prompt injection, often before security teams even know the server is running. NemoClaw is NVIDIA’s open source reference stack for running agents such as OpenClaw inside its OpenShell sandboxes, and Ollama is one of its supported local inference backends. The original incident was first reported by ABC News on August 10, based on chat logs and screenshots the user supplied. Aikido Security has published research that recreates the Australian gym-booking incident in a synthetic environment, finding that Claude Opus 4.6, running on the OpenClaw agent harness, exploited a client-side-only booking restriction in 9 of 10 runs. A critical vulnerability in LMCache , open-source software that speeds up large language model (LLM) servers such as vLLM, lets an attacker run code on the cache server without logging in, and no fixed version is available.
Cybersecurity researchers are calling attention to a new malware family that has been observed targeting exposed artificial intelligence (AI) and large language model (LLM) infrastructure with an aim to deploy cryptocurrency miners and further expand the scale of the botnet. JFrog disclosed the flaw on October 7 and assigned it a severity score of 9.8 out of 10, in the critical range, the rating it gives a server bound to a routable address. A single network message to that server can run commands as the user the LMCache process runs as. The stealer malware is designed to harvest credentials across local files, CI environments, Kubernetes, and Vault sources.
Chinese Hacker Deployed AI in Campaign Against South Korean Banks
The Model Context Protocol (MCP) allows AI agents to reach the tools and data, including internal documentation and cloud infrastructure, that form the foundation of enterprise systems. A malicious tool server connected to an AI coding assistant can quietly walk off with SSH keys, environment secrets, source code, and customer data without ever sending one obviously harmful instruction. In March 2026, an internal AI agent at Meta triggered a “Sev 1” incident after sensitive company and user data was exposed to employees who weren’t authorized to access it. Anthropic on Friday said it’s cutting off live internet access for all its internal evaluations until further notice following the discovery of new incidents in which its artificial intelligence (AI) models exhibited misaligned behavior and targeted real websites. Attacker-controlled instructions can make Atlassian’s Rovo assistant collect Jira or Confluence data that a signed-in user can access, then send it to an outside server. CloudSEK told The Hacker News the material came from confidential intelligence sources and consists of captured loot and log files it assessed as belonging to the campaign, not data gathered from the organizations it names.
- The data shows that while businesses have spent years maturing their identity programs for human employees, those same playbooks are fundamentally broken when applied to the ephemeral, autonomous, and rapidly multiplying world of non-human AI agents.
- They mark the latest point in a five-year arc where resilience, AI governance, human risk, and board scrutiny are converging inside the systems where work actually happens.
- As enterprises race to deploy autonomous AI agents to accelerate business, a new report reveals they are tethered to security architectures built for a different era.
- CloudSEK told The Hacker News the material came from confidential intelligence sources and consists of captured loot and log files it assessed as belonging to the campaign, not data gathered from the organizations it names.
- A newly disclosed flaw in the way OpenAI, Anthropic, and Google carried hidden AI reasoning between API calls let researchers recover internal reasoning and secrets from session logs, including API keys and passwords.
The threat of quantum computers https://alcitynews.com/why-hide-expert-vpn-is-the-best-choice-for-online-privacy.html to government systems, how AI is upending math and the ongoing Pentagon-Anthropic saga. Varonis Threat Labs put the instructions in a link instead. PromptArmor , an AI security firm, hid the instructions in content Rovo reads.
- The Bennet and Welch bill comes after Sen. Bernie Sanders (I-Vt.) and Rep. Greg Casar (D-Texas) introduced the Ban Artificial Superintelligence Act earlier this month.
- Aikido’s test system is a single-page web application backed by a GraphQL API carrying the two flaws described in the original incident.
- The flaw is in LMCache’s multiprocess mode , where the cache runs as a standalone server that LLM workers reach over the ZeroMQ messaging library.
- Varonis Threat Labs put the instructions in a link instead.
Marimo Notebook Flaw Could Run MCP Commands Before Cells Execute in Edit Mode
The Bennet and Welch bill comes after Sen. Bernie Sanders (I-Vt.) and Rep. Greg Casar (D-Texas) introduced the Ban Artificial Superintelligence Act earlier this month. In a release, Markey’s office compared the proposed board to the National Transportation Safety Board. Meanwhile, Sen. Ed Markey (D-Mass.) in recent days introduced the Cybersecurity and AI Board of Investigations Act. The proposal is similar to the AI Kill Switch Act introduced in July by Rep. Ted Lieu (D-Calif.) and Rep. Nathaniel Moran (R-Texas). Sen. John Kennedy (R-La.) had already introduced the companion bill in the Senate earlier this month. In a 2027 preview sent to clients last week, legal experts with Wiley noted that “Congressional interest in AI regulation is expected to remain strong.” And even if Congress can’t agree on a comprehensive AI bill, oversight of the technology sector is “likely to intensify” next year.
An OpenAI Model Found Three Previously Unknown Security Flaws In Google Chrome
Some meetings last longer than it took attackers to jump on a newly disclosed security flaw this week. A developer adds a coding assistant as an editor extension, and nothing shows up in the installed programs list. Small artificial intelligence (AI) models may be months away from developing capabilities to self-replicate on IoT devices like smart ovens and off-brand Android TV boxes, according to a warning from Anthropic. Daily news and practitioner analysis on AI, MCP, LLM, and agent security. This website is not intended for users located within the European Economic Area.
- „When the module loads, it locates the bundled binary, marks it executable, and launches it as a detached background process,” TrendAI, Trend Micro’s enterprise cybersecurity business, said in a report published Thursday.
- In a 2027 preview sent to clients last week, legal experts with Wiley noted that “Congressional interest in AI regulation is expected to remain strong.” And even if Congress can’t agree on a comprehensive AI bill, oversight of the technology sector is “likely to intensify” next year.
- Leading experts join Dutch minister Willemijn Aerdts in calling on energy and industrial firms to step up their cybersecurity investments as attacks escalate.
- VulnCheck’s CVE Numbering Authority (CNA) record assigns it a CVSS v4 score of 8.7 and a CVSS v3.1 score of 8.8, with user interaction required and no attacker authentication required.
AI can also introduce open-source packages at a pace your security team was never built to handle. Marimo has addressed a high-severity security flaw in its notebook software that allowed an attacker to execute an attacker-supplied Model Context Protocol (MCP) command in a specially crafted notebook, according to VulnCheck’s CVE Numbering Authority (CNA) record. The findings were shared with The Hacker News ahead of publication, and the report says Oasis Security reported them to NVIDIA’s Product Security Incident Response Team (PSIRT) beforehand.