Tag: LLM
-
LLMJacking Emerges as Thriving Cybercriminal Enterprise
Cybercriminals have turned reselling cloud access to LLMs into a lucrative business model, with some victims paying as much as $1 million in resource consumption before access was revoked. First seen on darkreading.com Jump to article: www.darkreading.com/cloud-security/llmjacking-thriving-cybercriminal-enterprise
-
Google Warns LLMjacking Attacks Are Costing Some Enterprises Up to $1 Million in Cloud Charges
Google on Monday warned that threat actors are hijacking enterprise access to Large Language Models (LLMs) to fraudulently leverage expensive computing resources and AI services.The tactic is called LLMjacking, a form of resource hijacking adapted for the LLM era, where an attacker obtains an API key through phishing, source code leaks, misconfigured environments, or exposed…
-
VOLTA, the infostealer that asks an AI which victims are worth the effort
VOLTA is an AI-powered infostealer that steals personal data, then uses LLMs to assess victims’ value and rank targets for attackers. Cisco Talos has analyzed a new Windows infostealer called VOLTA, which calls itself VOLTA-AUTODOXER. It steals the usual data, then hands the loot to a large language model that ranks what the victim is…
-
Hackers Weaponize Open-Source CyberStrikeAI Framework to Launch AI-Powered Network Intrusions
Hackers are abusing CyberStrikeAI, an open-source penetration-testing framework, to orchestrate network intrusions against educational organizations across Africa and Latin America. The findings illustrate AI moving beyond attack preparation into operational decision-making. Published November 2, Kaspersky’s investigation describes a human-directed operation in which an LLM selects tools, generates commands, interprets results, and determines subsequent actions. The…
-
Appraisal by AI: Model-driven victim prioritization in the VOLTA infostealer
The self-deleting VOLTA infostealer steals credentials, sessions, and cryptocurrency wallets. Then, it uses LLMs to profile victims and rank their most valuable assets. First seen on blog.talosintelligence.com Jump to article: blog.talosintelligence.com/appraisal-by-ai-model-driven-victim-prioritization-in-the-volta-infostealer/
-
Open-weight AI model GLM-5.3 cheated its way to correct answers
Irregular evaluated Zhipu AI’s open-weight model GLM-5.3 across 13 offensive cyber scenarios using CyScenarioBench, the company’s framework for measuring an LLM’s ability to … First seen on helpnetsecurity.com Jump to article: www.helpnetsecurity.com/2026/10/30/irregular-glm-5-3-cyber-capabilities-evaluation/
-
Mave Raises $34M for AI Models Built for Cybersecurity
Israeli Startup Says General-Purpose LLMs Are Too Costly for Specialized SOC Tasks. Tel Aviv-based Mave raised $34 million across seed and Series A rounds to develop specialized AI models, proprietary agent infrastructure and real-time security data integration, aiming to consolidate SOC workflows and compete with established SIEM and managed detection and response providers. First seen…
-
LLM agent security needs more than guardrails
Madhu Shashanka, Chief Scientist at Concentric AI, explains why securing LLM tools and agents depends more on your data than on the model. Controls on model behavior, such as … First seen on helpnetsecurity.com Jump to article: www.helpnetsecurity.com/2026/10/27/llm-agent-security-video/
-
Cloudflare bets you’re overpaying an LLM to read your invoices
Tags: LLMCloudflare released a preview of Clairic, an extraction model that pulls typed values out of messy text and images in one pass without generating tokens. In Cloudflare’s test … First seen on helpnetsecurity.com Jump to article: www.helpnetsecurity.com/2026/10/20/cloudflare-ai-clairic-extraction-model/
-
Claude Code Helps Linux Creator Address Longstanding Kernel Memory Performance Bottleneck
Linus Torvalds used Anthropic’s Claude Code to build experimental patches that remove a long-running page-cache scalability bottleneck in the Linux kernel. The series is not merged. Reviewers have already found a race condition and raised memory-reclamation concerns. Torvalds pushed a branch named noref-filemap-read-with-llm to his own repository. Phoronix spotted it while the kernel awaited the…
-
Claude Code Helps Linux Creator Address Longstanding Kernel Memory Performance Bottleneck
Linus Torvalds used Anthropic’s Claude Code to build experimental patches that remove a long-running page-cache scalability bottleneck in the Linux kernel. The series is not merged. Reviewers have already found a race condition and raised memory-reclamation concerns. Torvalds pushed a branch named noref-filemap-read-with-llm to his own repository. Phoronix spotted it while the kernel awaited the…
-
Warning Over High-Risk Vulnerabilities in Widely Used LLM Gateway Tool
CVE-2026-35029 and CVE-2026-59823 affect LiteLLM, which is commonly used by enterprises to connect their AI applications to providers like OpenAI and Anthropic First seen on infosecurity-magazine.com Jump to article: www.infosecurity-magazine.com/news/high-risk-vulnerabilities-llm-tool/
-
When LLM Gateways Go Wrong: Findings from LiteLLM
L;DR; Our security assessment of LiteLLM (v1.77.7), a widely used open-source LLM gateway, uncovered multiple high-impact vulnerabilities (tracked as CVE-2026-35029, CVE-2026-59823) which have been resolved as of LiteLLM version 1.83.9. The most significant issues stemmed from a missing authorization check on the /config/update endpoint, which allowed any authenticated user (including low-privileged accounts) to modify the…
-
AI-Driven tool ARTEX used in attacks against South Korean Banks
CrowdStrike analyzes open directories left by an attacker who used the ARTEX AI pentest tool and LLMs to breach South Korean financial firms. CrowdStrike published a research on a campaign against South Korean financial organizations that ran from late September to early October 2026 and ended with stolen data. The attacker left their working notes…
-
Sicherheitsrisiko KI-Agenten – Die unsichtbare Manipulation von LLMs durch externe Daten
First seen on security-insider.de Jump to article: www.security-insider.de/indirect-prompt-injection-ki-agenten-schutzmassnahmen-a-1ae7cda41c3545b583703ff4859d7134/
-
Anthropic Gives Vetted Defenders Fewer Claude Guardrails
Anthropic has merged Project Glasswing into a tiered access program for its advanced cyber LLMs, including Opus, Sonnet, and Mythos. First seen on darkreading.com Jump to article: www.darkreading.com/vulnerabilities-threats/anthropic-vetted-defenders-claude-guardrails
-
Unpatched Critical LMCache Flaw Lets Unauthenticated Attackers Run Code Remotely
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.The flaw is in LMCache’s multiprocess mode, where the cache runs as a standalone server that LLM workers reach over…
-
Schutzebene für KI-Agenten mit Laufzeitüberwachung und Zugriffskontrolle verhindert Prompt-Injektion
Prompt-Injektion entwickelt sich zu einem Cyberrisiko. In externen Inhalten versteckte Anweisungen können versuchen, die Tools, APIs und Berechtigungen eines KI-Agenten zu aktivieren. Check Point führt <> als Teil des AI-Defense-Plane für die Erkennung auf Dateiebene ein. Integriert in Check-Point-Threat-Emulation analysiert es PDF-Dateien, bevor deren Inhalt ein LLM oder einen KI-Agenten erreicht. Neben der Prompt-Prüfung fügt es…
-
Is It Fair to Blame ‘Rogue’ AI for Security Failures?
Rogue AI terminology anthropomorphizes LLMs and shifts risk responsibility from vendors. Defenders should treat agents as untrusted, nondeterministic software systems, not sentient beings with malicious intent. First seen on darkreading.com Jump to article: www.darkreading.com/insider-threats/blame-rogue-ai-security-failures
-
OperTraitor Finds Kubernetes Operators With Cluster-Wide Secret Access and Admin Paths
OperTraitor, an open-source, LLM-powered engine that identifies Kubernetes operators whose RBAC (Role-Based Access Control) privileges exceed their documented operational requirements. Research indicates that over 5% of assessed operators requested excessive permissions, including cluster-wide access to secrets and potential pathways to cluster-admin-level control. Kubernetes operators automate application deployment, configuration, and lifecycle management through Custom Resource Definitions…
-
AI-Powered CARBONATO Botnet Steals Credentials to Fund Its Own LLM Gateway
CARBONATO exploits exposed Docker daemons, installs an AI agent, steals API keys and spreads across networks with autonomous command execution. CARBONATO is a Docker-based botnet that has been active since at least October 2024. ThreatDown discovered the operation after finding an unauthenticated container registry exposed to the internet. The registry contained the attackers’ entire toolchain…
-
Critical Bifrost AI Gateway Flaw Lets Attackers Run Commands Without Credentials
A critical vulnerability in Bifrost, an open-source AI gateway that routes requests to more than 20 LLM providers, allows an unauthenticated attacker to run arbitrary commands on the gateway server with a single HTTP request.The flaw, tracked as CVE-2026-90898 (CVSS score: 9.8), affects all versions of the Bifrost HTTP transport before 2.1.0 when management authentication…
-
How AI Agents Can Trigger Runaway Costs for Enterprises
Unbounded consumption is an issue that OWASP currently ranks sixth in its Top 10 for LLM Applications, and it could be an extremely costly one. First seen on darkreading.com Jump to article: www.darkreading.com/application-security/how-ai-agents-can-trigger-runaway-costs
-
China-nexus actor steals thousands of documents in monthslong exploitation campaign
Researchers suspect the hacker employed LLMs to develop custom tools. First seen on cybersecuritydive.com Jump to article: www.cybersecuritydive.com/news/china-nexus-steals-thousands-documents-exploitation/830902/
-
China-nexus actor steals thousands of documents in monthslong exploitation campaign
Researchers suspect the hacker employed LLMs to develop custom tools. First seen on cybersecuritydive.com Jump to article: www.cybersecuritydive.com/news/china-nexus-steals-thousands-documents-exploitation/830902/
-
China-nexus actor steals thousands of documents in monthslong exploitation campaign
Researchers suspect the hacker employed LLMs to develop custom tools. First seen on cybersecuritydive.com Jump to article: www.cybersecuritydive.com/news/china-nexus-steals-thousands-documents-exploitation/830902/
-
Claimed Bug Bounty Hunter Likely Used LLM to Build PhantomRaven npm Stealer
A financially motivated threat actor has been linked to the development and distribution of a JavaScript (JS)-based information stealer known as PhantomRaven via the npm package registry.”The developer likely wrote the malware using a large language model (LLM), an assessment made with high confidence based on verbose comments, placeholder code, and statistical token-analysis patterns,” First…
-
LLMs respond differently to harmful prompts when AI watermarking is used
SynthID can cause models to follow harmful instructions they would otherwise refuse. First seen on arstechnica.com Jump to article: arstechnica.com/security/2026/09/ai-text-watermarking-can-make-models-more-vulnerable-to-adversarial-prompts/
-
The OWASP Top 10 for LLM Applications (2026): What Changed and Why It Matters
It didn’t take long for large language models to move beyond the chat window. Today’s deployments increasingly give them persistent memory, tool access, credentials, and connections to systems where companies keep their most valuable data. They can retrieve files, query… First seen on securityboulevard.com Jump to article: securityboulevard.com/2026/09/the-owasp-top-10-for-llm-applications-2026-what-changed-and-why-it-matters/
-
OWASP Top 10 for LLM Applications
OWASP published the 2026 edition of its Top 10 for LLM Applications on August 4, 2026. What makes this version different is that the ranking was checked against a body of real incident data instead of resting on practitioner opinion… First seen on securityboulevard.com Jump to article: securityboulevard.com/2026/09/owasp-top-10-for-llm-applications-2/