Tag: LLM
-
Sysdig Details JADEPUFFER, the First Documented Agentic Ransomware Operation
A new Sysdig report traces how an LLM agent abused a Langflow flaw, stole credentials, reached production MySQL, and destroyed Nacos config data in minutes flat. First seen on hackread.com Jump to article: hackread.com/sysdig-jadepuffer-first-agentic-ransomware-operation/
-
JADEPUFFER Agentic Ransomware Uses LLM to Automate Database Extortion
The first instance of agentic ransomware: JADEPUFFER, an LLM-driven extortion operation that automated an end-to-end database-crippling campaign. The actor gained execution on an internet-facing Langflow instance via CVE-2025-3248, used the AI-host environment to harvest cloud and API credentials, and pivoted into a production MySQL/Nacos deployment to carry out a destructive, database-focused extortion playbook without a…
-
‘Phantom Squatting’: An Emerging AI-Driven Supply Chain Threat
LLMs consistently hallucinate Web domains for legitimate brands that attackers can register for malicious activity in a difficult-to-detect attack vector. First seen on darkreading.com Jump to article: www.darkreading.com/endpoint-security/phantom-squatting-ai-driven-supply-chain-threat
-
Browser-Only Ransomware: From LLM Hallucinations to a Practical Attack Technique
Tags: ai, attack, chatgpt, cybercrime, LLM, malicious, malware, programming, ransomware, software, toolesearch by:Alexey Bukhteyev Key Takeaways Introduction Over the past several years, large language models have reshaped software development, and malware development has followed the same path. Check Point Research has documented this trend from early experiments showing that AI systems could generate offensive components, to cases of cybercriminals using ChatGPT to create malicious tools, and…
-
Attackers Register AI-Hallucinated Domains to Deliver Phishing Kits and Malware
An emergent supply-chain attack vector they term >>phantom squatting,<< in which large language models (LLMs) routinely hallucinate plausible but nonexistent domains for legitimate brands and adversaries then preemptively register those domains to host phishing kits, malware, and other malicious infrastructure. By systematically probing two distinct LLM families across temperature settings, Unit 42 generated a 2.1…
-
AI-Powered Reverse Engineering Turns EDR Rule Analysis Into Automated Evasion Workflow
LLMs are reshaping endpoint security research by turning what used to be slow, manual reverse engineering into an automated, repeatable evasion workflow. Recent hands-on experiments with advanced models driving disassembly and local analysis show that a compact harness LLM plus disassembler, a shared state file, and a loop can recover EDR artifacts, decrypt local signature…
-
New attack provides one more reason why AI browsers are a bad idea
Telling an LLM that 2 + 2 = 5 is enough to make it follow forbidden instructions. First seen on arstechnica.com Jump to article: arstechnica.com/security/2026/06/ai-browsers-can-be-lulled-into-a-dream-world-where-guardrails-no-longer-apply/
-
AI-Generated Mythic Agents Challenge Static Signatures and Traditional Implant Detection
The emergence of LLM-driven >>disposable tooling<< is reshaping offensive tradecraft and forcing defenders to rethink detection models that rely on static signatures and known implant behaviors. Recent experiments demonstrating the automated generation of Mythic agents from prompt to deployment reveal a new threat class: ephemeral, single-use implants tailor-made by large language models and orchestration harnesses.…
-
Companies keep bolting AI onto their products, and the security bill is coming due
Companies keep bolting AI and LLM features onto their products, and the security results are starting to show a pattern. The vulnerabilities those features create get rated … First seen on helpnetsecurity.com Jump to article: www.helpnetsecurity.com/2026/06/29/products-ai-pentesting/
-
AI Firms Seek US Help Against China Model Distillation
Anthropic Says Legal Gaps Leave Frontier Labs Vulnerable to LLM Copying. U.S.-based AI companies are urging the U.S. government to crack down on alleged illicit model distillation by Chinese AI developers, arguing current protections lack enforcement. Anthropic and others say legal reforms and clearer antitrust rules are needed to deter theft of frontier AI models.…
-
LLM security advice looks solid until you check the hard cases
Plenty of people now type their security worries straight into a chatbot. A hacked account, a suspicious email, a stalker who might be tracking a phone, all of it lands in the … First seen on helpnetsecurity.com Jump to article: www.helpnetsecurity.com/2026/06/25/helpbench-llm-security-advice/
-
282 iOS Apps Found Leaking LLM API Credentials in Network Traffic
Researchers have uncovered a systemic LLM credential exposure problem in the iOS ecosystem, with 282 AI”‘powered apps leaking exploitable API credentials and backend access mechanisms directly in network traffic. The findings highlight widespread misuse of OpenAI, Gemini, and other LLM provider APIs in mobile apps and show that many issues remain unpatched even after responsible…
-
Critical Copilot vulnerability allowed hackers to steal 2FA code from users
SearchLeak exploit shows why the industry’s approach to LLM security fails over and over. First seen on arstechnica.com Jump to article: arstechnica.com/security/2026/06/critical-copilot-vulnerability-allowed-hackers-to-seal-2fa-code-from-users/
-
Critical Copilot vulnerability allowed hackers to seal 2FA code from users
SearchLeak exploit shows why the industry’s approach to LLM security fails over and over. First seen on arstechnica.com Jump to article: arstechnica.com/security/2026/06/critical-copilot-vulnerability-allowed-hackers-to-seal-2fa-code-from-users/
-
KI-Sicherheit im Unternehmen: Warum LLMs, KI-Pipelines und Agenten neue Schutzmechanismen brauchen
In vielen Unternehmen läuft generative KI inzwischen im Hintergrund mit, als Chatbot, als Wissensassistent, im Code-Editor und immer öfter als Agent, der eigenständig Systeme anspricht und Daten abruft. Mit jeder dieser Integrationen wächst eine Angriffsfläche, die vorhandene Sicherheitswerkzeuge allein nicht ausreichend abdecken. Firewall, Authentifizierung und Eingabefilter bleiben notwendig, für LLM-, RAG- und agentenbasierte […] First…
-
Openclaw durch Prompt-Injection in Nachrichtenobjekten angreifbar
Die Sicherheitsforscher von Thales haben Sicherheitslücken auf Basis von Prompt-Injection bei Openclaw gefunden. Diese Schwachstellen wurden dem Openclaw-Sicherheitsteam verantwortungsbewusst gemeldet und mit Version 2026.4.23 wurde ein entsprechender Fix bereitgestellt. Dennoch bleiben zwei Herausforderungen bestehen: Prompt-Injection ist ein branchenweit weitgehend ungelöstes Problem. Es gibt keinen Standard, der regelt, wie Messaging-Objekte serialisiert werden, bevor sie ein LLM…
-
Warum LLMs, KI-Pipelines und Agenten neue Schutzmechanismen brauchen
In vielen Unternehmen läuft generative KI inzwischen im Hintergrund mit, als Chatbot, als Wissensassistent, im Code-Editor und immer öfter als Agent, der eigenständig Systeme anspricht und Daten abruft. Mit jeder dieser Integrationen wächst eine Angriffsfläche, die vorhandene Sicherheitswerkzeuge allein nicht ausreichend abdecken. Firewall, Authentifizierung und Eingabefilter bleiben notwendig, für LLM-, RAG- und agentenbasierte […] First…
-
Understanding LLM Coding Personalities Is Now Key to Developer Improvement
Organizations must understand AI coding models’ strengths, weaknesses, and security blind spots to reduce risk. First seen on esecurityplanet.com Jump to article: www.esecurityplanet.com/threats/understanding-llm-coding-personalities-is-now-key-to-developer-improvement/
-
How to defend at machine speed: A post-LLM era playbook
Tags: LLMFirst seen on scworld.com Jump to article: www.scworld.com/native/how-to-defend-at-machine-speed-a-post-llm-era-playbook
-
AI red teaming agents change how LLMs get tested
Adversarial probing of LLMs has piled up a sprawling toolkit over the past three years. Attack techniques with names like Tree of Attacks with Pruning, Crescendo, and Skeleton … First seen on helpnetsecurity.com Jump to article: www.helpnetsecurity.com/2026/05/21/ai-red-teaming-agents-research/
-
The AI backdoor your security stack is not built to see
Enterprises deploying LLMs have spent the past two years building defenses around a reasonable assumption: malicious behavior leaves a trace in the input. Scan for suspicious … First seen on helpnetsecurity.com Jump to article: www.helpnetsecurity.com/2026/05/18/metabackdoor-llm-backdoor-attack/
-
The AI backdoor your security stack is not built to see
Enterprises deploying LLMs have spent the past two years building defenses around a reasonable assumption: malicious behavior leaves a trace in the input. Scan for suspicious … First seen on helpnetsecurity.com Jump to article: www.helpnetsecurity.com/2026/05/18/metabackdoor-llm-backdoor-attack/
-
Okta Studie zeigt: Eingebaute KI-Guardrails reichen nicht aus
In einem Szenario genügte bereits ein simples Webformular auf einer präparierten Website, um ein unzensiertes LLM dazu zu bringen, seinen kompletten Credential-Store offenzulegen. First seen on infopoint-security.de Jump to article: www.infopoint-security.de/okta-studie-zeigt-eingebaute-ki-guardrails-reichen-nicht-aus/a45091/
-
Linux kernel maintainers suggest a ‘kill switch’ to protect systems until a zero-day vulnerability is patched
Tags: access, attack, business, control, cve, cybersecurity, exploit, flaw, group, incident response, infosec, linux, LLM, mitigation, risk, service, strategy, switch, technology, tool, update, vulnerability, zero-day), a logic bug which lets users easily obtain root access, and Dirty Frag, which abuses weaknesses in how the Linux kernel handles fragmented memory pages. The Dirty Frag attack combines two separate vulnerabilities affecting the Linux IPsec Encapsulating Security Payload (ESP) subsystem (CVE-2026-43284) and the RxRPC networking protocol (CVE-2026-43500). The proposal has set off a furious…
-
AI Researchers Target SIEM Migration Bottleneck
System Translates Detection Rules Across Security Platforms. Researchers developed an AI framework that converts threat detection rules between major SIEM platforms including Splunk, Microsoft Sentinel and QRadar. The system uses LLMs and automated validation steps to preserve detection logic during migrations that often require months of manual work. First seen on govinfosecurity.com Jump to article:…
-
AI security is repeating endpoint security’s biggest mistake
Tags: access, ai, api, automation, business, control, data, detection, edr, endpoint, governance, incident response, injection, LLM, monitoring, open-source, radius, risk, saas, sbom, soc, strategy, technology, threat, tool, updateMost AI security is still at the posture phase: Look at where most organizations are with AI security today. Model cards, AI-specific SBOMs, input and output filters, prompt injection guardrails and access controls around model APIs. These are valuable controls, but they reflect a posture-based approach. To truly enhance security, organizations must recognize the importance…
-
1,800+ MCP servers exposed without authentication: How zero trust can secure the AI agent revolution
Tags: ai, attack, authentication, breach, cloud, control, credentials, data, data-breach, defense, exploit, framework, governance, identity, infrastructure, Internet, LLM, malicious, monitoring, network, risk, service, supply-chain, threat, tool, vulnerability, zero-trustThe epistemological chasm: What renders MCP vulnerabilities particularly vexatious is the fundamental asymmetry they exploit between machine cognition and human oversight.Tool poisoning attacks insert malevolent instructions into tool metadata that LLMs process with complete fidelity but that remain utterly invisible to human operators. The machine perceives everything; its ostensible supervisors perceive nothing. We have unwittingly…
-
OpenAI and Anthropic LLMs Used in Critical Infrastructure Cyber-Attack, Warns Dragos
Commercial AI models were used to help plan and conduct cyber-attack against operational technology of a water and drainage facility, say researchers First seen on infosecurity-magazine.com Jump to article: www.infosecurity-magazine.com/news/llm-critical-infrastructure/
-
Poisoned truth: The quiet security threat inside enterprise AI
It takes surprisingly little poison to corrupt: Bad internal data is the immediate problem. But the external supply chain may be even harder to control.Research by Anthropic, the UK AI Security Institute, and the Alan Turing Institute discovered that as few as 250 maliciously crafted documents can poison LLMs of any size.That creates a massive…