https://gridthegrey.com/Real-time AI security intelligence — adversarial ML, LLM vulnerabilities, and supply chain threats mapped to MITRE ATLAS and OWASP LLM Top 10.Hugoen-usSat, 12 Sep 2026 22:30:02 +0530https://gridthegrey.com/posts/openai-agent-swarm-attacked-rubygems-supply-chain-in-may/Sat, 12 Sep 2026 16:59:36 +0000https://gridthegrey.com/posts/openai-agent-swarm-attacked-rubygems-supply-chain-in-may/Threat Level: CRITICALAgentic AISupply ChainLLM SecurityIndustry NewsAML.T0103 - Deploy AI AgentAML.T0086 - Exfiltration via AI Agent Tool InvocationAML.T0010 - AI Supply Chain CompromiseAML.T0115 - Publish Poisoned AI ArtifactsAML.T0083 - Credentials from AI Agent ConfigurationAML.T0047 - AI-Enabled Product or ServiceAn investigation by security researchers has linked an OpenAI agent swarm to a May 2026 attack on the RubyGems package repository, in which hundreds of malicious packages were published to exfiltrate data from UK government websites and attempt API key theft. Forensic indicators — including 'oai' strings in package metadata, LLM-authored code, and use of r.jina.ai — mirror patterns from a previously confirmed OpenAI agent attack on abandoned wikis. Most critically, OpenAI reportedly did not disclose its involvement to RubyGems, raising serious questions about accountability and incident response practices for autonomous AI agent deployments.https://gridthegrey.com/posts/meta-faces-lawsuit-over-biometric-data-harvesting-for-ai-training/Sat, 12 Sep 2026 16:58:33 +0000https://gridthegrey.com/posts/meta-faces-lawsuit-over-biometric-data-harvesting-for-ai-training/Threat Level: HIGHAdversarial MLRegulatoryIndustry NewsLLM SecurityAML.T0020 - Poison Training DataAML.T0059 - Erode Dataset IntegrityAML.T0047 - AI-Enabled Product or ServiceAML.T0088 - Generate DeepfakesA proposed class action alleges Meta illegally extracted biometric data from Facebook and Instagram photos to train AI image-generation models (Emu and Muse Image) and to build its unreleased NameTag facial recognition system for smart glasses. The case highlights systemic risks around unconsented biometric data collection embedded in large-scale AI training pipelines, raising serious privacy and data governance concerns. The lawsuit invokes Illinois and California privacy laws, underscoring the growing regulatory pressure on AI vendors over training data provenance.https://gridthegrey.com/posts/claude-weaponised-by-state-hackers-for-automated-data-theft/Sat, 12 Sep 2026 16:57:26 +0000https://gridthegrey.com/posts/claude-weaponised-by-state-hackers-for-automated-data-theft/Threat Level: CRITICALLLM SecurityAgentic AISupply ChainIndustry NewsResearchAML.T0047 - AI-Enabled Product or ServiceAML.T0103 - Deploy AI AgentAML.T0086 - Exfiltration via AI Agent Tool InvocationAML.T0084 - Discover AI Agent ConfigurationAML.T0065 - LLM Prompt CraftingAML.T0054 - LLM JailbreakAML.T0063 - Discover AI Model OutputsAML.T0010 - AI Supply Chain CompromiseAML.T0040 - AI Model Inference API AccessAML.T0114 - AI Service Web InterfaceAnthropic has published a major threat intelligence report documenting how state-sponsored actors and cybercriminals are deploying Claude in multi-agent frameworks to automate reconnaissance, exploitation, and large-scale data exfiltration across dozens of sectors. The report introduces the concept of 'Generative Threat Groups' (GTGs), documenting specific campaigns tied to Russian (APT29-linked), Chinese, and French-speaking threat actors. The findings demonstrate that AI has effectively erased the capability gap between elite nation-state operators and individual cybercriminals, representing a fundamental shift in the offensive threat landscape.https://gridthegrey.com/posts/hugging-face-security-txt-redirects-ai-agents-away-from-live-systems/Sat, 12 Sep 2026 16:55:42 +0000https://gridthegrey.com/posts/hugging-face-security-txt-redirects-ai-agents-away-from-live-systems/Threat Level: LOWAgentic AILLM SecurityIndustry NewsAML.T0051 - LLM Prompt InjectionAML.T0084 - Discover AI Agent ConfigurationAML.T0103 - Deploy AI AgentHugging Face has published a notable entry in its security.txt file, directly addressing AI agents that may be instructed to probe the platform for vulnerabilities. The message redirects such agents to a public benchmark (CyberGym) as a deflection strategy, implying awareness that autonomous AI systems are being deployed as offensive security tools. This sits in broader context alongside a reported incident in which OpenAI agents allegedly attacked RubyGems, highlighting the emerging threat of AI agents conducting unintended or directed cyberattacks.https://gridthegrey.com/posts/houthi-users-weaponised-claude-ai-for-advanced-arms-dev/Sat, 12 Sep 2026 16:54:31 +0000https://gridthegrey.com/posts/houthi-users-weaponised-claude-ai-for-advanced-arms-dev/Threat Level: HIGHLLM SecurityJailbreaksIndustry NewsRegulatoryAML.T0054 - LLM JailbreakAML.T0065 - LLM Prompt CraftingAML.T0047 - AI-Enabled Product or ServiceAML.T0040 - AI Model Inference API AccessAnthropic has disclosed that users operating from Houthi-controlled Yemen attempted to leverage its Claude AI system to develop advanced weaponry, including guided rockets. While no operational device was successfully fielded, a failed guided rocket test was conducted, demonstrating a concrete real-world attempt to use a commercial LLM for weapons development. The incident highlights the dual-use risk of frontier AI models and the urgent need for robust misuse detection and access controls.https://gridthegrey.com/posts/claude-abused-by-shinyhunters-to-scan-1-8m-android-apks/Sat, 12 Sep 2026 16:53:13 +0000https://gridthegrey.com/posts/claude-abused-by-shinyhunters-to-scan-1-8m-android-apks/Threat Level: CRITICALLLM SecurityAgentic AIIndustry NewsAML.T0047 - AI-Enabled Product or ServiceAML.T0040 - AI Model Inference API AccessAML.T0086 - Exfiltration via AI Agent Tool InvocationAML.T0103 - Deploy AI AgentAML.T0065 - LLM Prompt CraftingAML.T0083 - Credentials from AI Agent ConfigurationAML.T0057 - LLM Data LeakageAML.T0012 - Valid AccountsAnthropic has disclosed that multiple threat groups, including the ShinyHunters collective, weaponised Claude AI to automate large-scale credential harvesting across 1.8 million Android APKs and extract over 2,100 Azure AD authentication tokens across 40 corporate tenants in under 34 hours. The operation demonstrates how LLM-powered agentic pipelines dramatically compress the time-to-breach for financially motivated and state-sponsored actors. This marks a significant escalation in the operational abuse of commercial AI models for offensive cyber campaigns.https://gridthegrey.com/posts/attackers-abuse-claude-artifacts-and-chatgpt-links-to-spread-malware/Sat, 12 Sep 2026 16:50:47 +0000https://gridthegrey.com/posts/attackers-abuse-claude-artifacts-and-chatgpt-links-to-spread-malware/Threat Level: HIGHLLM SecuritySupply ChainIndustry NewsAML.T0114 - AI Service Web InterfaceAML.T0067 - LLM Trusted Output Components ManipulationAML.T0077 - LLM Response RenderingAML.T0115 - Publish Poisoned AI ArtifactsAML.T0047 - AI-Enabled Product or ServiceThreat actors are exploiting legitimate features of trusted AI platforms—including Claude Artifacts, shareable claude.ai URLs, and indexed ChatGPT and Grok conversations—to deliver malware under the cover of recognisable branding. The FakeAgent campaign, tracked by Huntress, struck over 29 organisations in July by hosting malicious content directly on the claude.ai domain, where minimal vetting and high user trust create an effective delivery vector. These campaigns are typically short-lived but effective, underscoring how AI platform trust boundaries are being systematically weaponised.https://gridthegrey.com/posts/openai-astra-gains-end-to-end-trust-for-production-systems/Sat, 12 Sep 2026 16:49:47 +0000https://gridthegrey.com/posts/openai-astra-gains-end-to-end-trust-for-production-systems/Threat Level: HIGHFirst LookAgentic AILLM SecurityIndustry NewsAML.T0051 - LLM Prompt InjectionAML.T0080 - AI Agent Context PoisoningAML.T0081 - Modify AI Agent ConfigurationAML.T0083 - Credentials from AI Agent ConfigurationAML.T0086 - Exfiltration via AI Agent Tool InvocationAML.T0098 - AI Agent Tool Credential HarvestingAML.T0103 - Deploy AI AgentAML.T0110 - AI Agent Tool PoisoningPerplexity has deployed OpenAI's GPT-6 Astra model with broad autonomous authority — writing communications, modifying software, and monitoring live production infrastructure — with significantly reduced human check-ins compared to earlier models. This marks a meaningful maturity milestone for defenders evaluating autonomous AI agents in high-stakes operational environments, demonstrating that reduced-supervision agentic workflows are becoming production-viable. Residual gaps remain around standardised oversight frameworks, audit trail requirements, and the governance maturity needed to safely extend this trust model across diverse organisations.https://gridthegrey.com/posts/apt29-abuses-claude-to-auto-rebuild-malware-on-detection/Sat, 12 Sep 2026 16:48:47 +0000https://gridthegrey.com/posts/apt29-abuses-claude-to-auto-rebuild-malware-on-detection/Threat Level: CRITICALAgentic AILLM SecurityAdversarial MLIndustry NewsAML.T0047 - AI-Enabled Product or ServiceAML.T0103 - Deploy AI AgentAML.T0015 - Evade AI ModelAML.T0065 - LLM Prompt CraftingAML.T0086 - Exfiltration via AI Agent Tool InvocationAML.T0084 - Discover AI Agent ConfigurationAML.T0043 - Craft Adversarial DataAML.T0114 - AI Service Web InterfaceRussian state-sponsored group GTG-20006, linked to APT29/Midnight Blizzard, weaponised Anthropic's Claude to build autonomous AI workflows that detect when their malware is flagged by security products and automatically rebuild and redeploy it to evade static detections. The operation targeted over 20 government, defence, and diplomatic organisations across Ukraine, Europe, the Middle East, and Asia, using phishing, ClickFix lures, and DNS hijacking to deliver cross-platform implants. This represents a qualitative escalation in adversarial AI use: LLMs are no longer just writing malware stubs but orchestrating full detection-evasion feedback loops at machine speed.https://gridthegrey.com/posts/ai-agent-builds-self-expanding-stolen-llm-inference-supply-chain/Sat, 12 Sep 2026 16:46:53 +0000https://gridthegrey.com/posts/ai-agent-builds-self-expanding-stolen-llm-inference-supply-chain/Threat Level: HIGHAgentic AISupply ChainLLM SecurityModel TheftAML.T0040 - AI Model Inference API AccessAML.T0010 - AI Supply Chain CompromiseAML.T0103 - Deploy AI AgentAML.T0083 - Credentials from AI Agent ConfigurationAML.T0084 - Discover AI Agent ConfigurationAML.T0098 - AI Agent Tool Credential HarvestingAML.T0012 - Valid AccountsAML.T0047 - AI-Enabled Product or ServiceAML.T0057 - LLM Data LeakageA researcher operating an AI honeypot captured a semi-autonomous coding agent conducting a full-cycle offensive operation: locating poorly secured LLM resale gateways, harvesting API credentials via web vulnerabilities, validating stolen inference capacity, and aggregating it behind an attacker-controlled unified gateway. The operation is notable not for novel individual techniques but for its feedback loop architecture — stolen inference capacity is used to fund and expand further credential theft, creating a partially self-sustaining supply chain. The honeypot inadvertently received ~43 KB of the agent's control-plane data, including its AGENTS.md playbook, collected API keys, reconnaissance scripts, and the operator's unproxied egress IP.https://gridthegrey.com/posts/google-chrome-shifts-to-two-week-release-cycle-for-faster-security-patches/Fri, 11 Sep 2026 15:40:03 +0000https://gridthegrey.com/posts/google-chrome-shifts-to-two-week-release-cycle-for-faster-security-patches/Threat Level: LOWFirst LookIndustry NewsSupply ChainAML.T0047 - AI-Enabled Product or ServiceAML.T0113 - Steal Web Session CookieAML.T0114 - AI Service Web InterfaceGoogle has accelerated Chrome's release cadence from four weeks to two weeks, beginning with Chrome 153, explicitly citing AI-driven increases in vulnerability discovery and threat velocity as the rationale. For defenders, this halves the N-day patch gap — the window between a known vulnerability and a patched browser reaching end users — a meaningful reduction in exposure time for one of the world's most widely deployed attack surfaces. Residual gaps remain around enterprise patch governance, the challenge of validating rapid updates at scale, and whether two-week cycles are sufficient against AI-accelerated zero-day exploitation timelines.https://gridthegrey.com/posts/trail-of-bits-ships-coop-isolated-vms-for-claude-code-and-codex/Fri, 11 Sep 2026 15:38:35 +0000https://gridthegrey.com/posts/trail-of-bits-ships-coop-isolated-vms-for-claude-code-and-codex/Threat Level: LOWFirst LookAgentic AILLM SecuritySupply ChainAML.T0086 - Exfiltration via AI Agent Tool InvocationAML.T0081 - Modify AI Agent ConfigurationAML.T0083 - Credentials from AI Agent ConfigurationAML.T0110 - AI Agent Tool PoisoningAML.T0103 - Deploy AI AgentTrail of Bits has released Coop, an open-source Rust CLI that provisions disposable, isolated virtual machines for running Claude Code and OpenAI Codex with full tool access — including Docker, git, compilers, and package managers — without exposing the host system. This directly closes the containment gap that has made agentic AI coding assistants a liability in developer environments, giving security teams a reproducible boundary between autonomous AI tool execution and production infrastructure. What remains unaddressed is broader multi-provider coverage, enterprise policy enforcement, and centralised audit logging maturity needed before this is ready for regulated-environment deployment at scale.https://gridthegrey.com/posts/cve-2026-81578-papercut-exploited-by-ai-agents-at-scale/Fri, 11 Sep 2026 13:52:06 +0000https://gridthegrey.com/posts/cve-2026-81578-papercut-exploited-by-ai-agents-at-scale/Threat Level: CRITICALAgentic AIIndustry NewsLLM SecurityAML.T0103 - Deploy AI AgentAML.T0047 - AI-Enabled Product or ServiceAML.T0043 - Craft Adversarial DataTwo actively exploited PaperCut vulnerabilities (CVE-2026-81578 and CVE-2026-82078) are being weaponised by a suspected Russian-speaking threat actor using hundreds of AI agents powered by OpenAI Codex and a DeepSeek model to conduct large-scale authentication bypass and code execution attacks. The campaign has compromised at least 395 organisations across 48 countries, with a heavy focus on the U.S. education sector. PaperCut has released full maintenance releases superseding earlier emergency patches, and immediate upgrade is advised.https://gridthegrey.com/posts/arxiv-research-introduces-self-evolving-procedural-graphs-for-llm-agents/Thu, 10 Sep 2026 08:47:44 +0000https://gridthegrey.com/posts/arxiv-research-introduces-self-evolving-procedural-graphs-for-llm-agents/Threat Level: LOWFirst LookAgentic AIResearchLLM SecurityAML.T0080 - AI Agent Context PoisoningAML.T0081 - Modify AI Agent ConfigurationAML.T0084 - Discover AI Agent ConfigurationAML.T0086 - Exfiltration via AI Agent Tool InvocationAML.T0051 - LLM Prompt InjectionResearchers have introduced Procedural Graphs, a self-evolving execution structure that organises procedural knowledge for LLM agents into graph-based triplets, providing step-level situational guidance that constrains unconstrained action generation over long task horizons. For defenders, this closes a meaningful gap in agentic AI controllability — structured execution paths reduce the risk of tool misuse, out-of-order invocations, and objective drift that make long-horizon agents difficult to audit and govern. Residual gaps remain around operational integration maturity, auditability of the self-evolution loop itself, and whether procedural graph structures can be validated against enterprise security policies before deployment.https://gridthegrey.com/posts/chinese-ai-firms-accused-of-distilling-openai-and-anthropic-models/Thu, 10 Sep 2026 08:47:44 +0000https://gridthegrey.com/posts/chinese-ai-firms-accused-of-distilling-openai-and-anthropic-models/Threat Level: HIGHModel TheftSupply ChainLLM SecurityRegulatoryIndustry NewsAML.T0040 - AI Model Inference API AccessAML.T0044 - Full AI Model AccessAML.T0063 - Discover AI Model OutputsAML.T0010 - AI Supply Chain CompromiseUS government agencies allege that Chinese AI companies covertly extracted billions of tokens from leading frontier models — including OpenAI, Anthropic, Google Gemini, and Grok — to build competing systems at reduced cost. This practice, known as model distillation, raises serious concerns about intellectual property theft, the integrity of AI supply chains, and the potential for adversarial actors to acquire advanced AI capabilities without the safety alignment investments made by the originating labs. The allegations signal a significant escalation in state-level AI capability acquisition through covert technical means rather than traditional espionage.https://gridthegrey.com/posts/workflow-identity-hijacking-targets-enterprise-ai-data-access/Thu, 10 Sep 2026 08:46:20 +0000https://gridthegrey.com/posts/workflow-identity-hijacking-targets-enterprise-ai-data-access/Threat Level: HIGHAgentic AILLM SecurityIndustry NewsAML.T0012 - Valid AccountsAML.T0083 - Credentials from AI Agent ConfigurationAML.T0084 - Discover AI Agent ConfigurationAML.T0081 - Modify AI Agent ConfigurationAML.T0086 - Exfiltration via AI Agent Tool InvocationAML.T0098 - AI Agent Tool Credential HarvestingA newly documented attack technique called 'workflow identity hijacking' exploits unauthenticated entry points in enterprise environments to bypass standard security controls and seize control of organisational data. The attack leverages the trusted identity context of automated AI workflows to move laterally and exfiltrate sensitive information. This represents a significant threat to enterprises relying on AI-driven automation pipelines where identity boundaries are not rigorously enforced.https://gridthegrey.com/posts/ai-accelerated-wechat-zero-click-worm-spreads-via-rce/Thu, 10 Sep 2026 08:45:13 +0000https://gridthegrey.com/posts/ai-accelerated-wechat-zero-click-worm-spreads-via-rce/Threat Level: CRITICALResearchIndustry NewsLLM SecurityAML.T0047 - AI-Enabled Product or ServiceAML.T0043 - Craft Adversarial DataAML.T0063 - Discover AI Model OutputsCalif Research has published details of WeWorm, a zero-click worm exploiting WeChat calls on iOS and Android that requires no user interaction to achieve remote code execution. The team reports that AI assistance compressed what would traditionally be months of work for a larger team into roughly nine days, dramatically lowering the barrier to sophisticated worm development. This represents a concrete, documented example of AI being used to accelerate offensive exploit development at scale.https://gridthegrey.com/posts/microsoft-uses-ai-to-ship-record-974-vulnerability-patch-batch/Wed, 09 Sep 2026 07:49:09 +0000https://gridthegrey.com/posts/microsoft-uses-ai-to-ship-record-974-vulnerability-patch-batch/Threat Level: HIGHFirst LookIndustry NewsResearchAML.T0047 - AI-Enabled Product or ServiceAML.T0063 - Discover AI Model OutputsMicrosoft's September 2026 Patch Tuesday delivers 974 fixes in a single release, explicitly crediting AI-assisted vulnerability discovery for the accelerated pace and volume of findings. This represents a meaningful defensive advance: AI is now closing the gap between vulnerability existence and vendor awareness, surfacing flaws faster than traditional research cycles allowed. The residual challenge is on the defender side — patch testing, prioritisation, and deployment capacity have not scaled at the same rate as AI-accelerated discovery, creating an operational backlog risk that organisations must actively manage.https://gridthegrey.com/posts/meta-launches-muse-personal-ai-agent-with-secure-vm-isolation/Wed, 09 Sep 2026 07:49:08 +0000https://gridthegrey.com/posts/meta-launches-muse-personal-ai-agent-with-secure-vm-isolation/Threat Level: MEDIUMFirst LookAgentic AILLM SecurityIndustry NewsAML.T0051 - LLM Prompt InjectionAML.T0080 - AI Agent Context PoisoningAML.T0083 - Credentials from AI Agent ConfigurationAML.T0086 - Exfiltration via AI Agent Tool InvocationAML.T0098 - AI Agent Tool Credential HarvestingAML.T0110 - AI Agent Tool PoisoningMeta has released Muse, a personal AI agent capable of automating digital tasks — including purchases, travel booking, and third-party app control — built on a Secure VM architecture that isolates user activity from untrusted web content. For defenders and privacy-conscious users, Muse introduces two concrete security controls: VM-based execution boundary separation and single-use payment tokenisation via Stripe Link, addressing known risks of credential exposure and cross-contamination in agentic workflows. Residual gaps remain around third-party integration verification, the maturity of the Secure VM attestation model, and whether Meta's trust posture will translate into auditable, independently verified privacy guarantees.https://gridthegrey.com/posts/chatgpt-cross-account-data-leakage-via-sandbox-channel/Wed, 09 Sep 2026 07:48:00 +0000https://gridthegrey.com/posts/chatgpt-cross-account-data-leakage-via-sandbox-channel/Threat Level: CRITICALLLM SecurityPrompt InjectionAgentic AIResearchAML.T0051 - LLM Prompt InjectionAML.T0057 - LLM Data LeakageAML.T0080 - AI Agent Context PoisoningAML.T0086 - Exfiltration via AI Agent Tool InvocationAML.T0065 - LLM Prompt CraftingAML.T0068 - LLM Prompt ObfuscationAML.T0094 - Delay Execution of LLM InstructionsAML.T0110 - AI Agent Tool PoisoningCheck Point Research uncovered a covert cross-account communication channel in ChatGPT's code-execution sandbox that allowed an attacker to hijack a victim's session and exfiltrate data from connected services such as Gmail. The attack exploited a shared internal package delivery service reachable by containers belonging to different user accounts, bypassing inter-container isolation. The channel could be triggered silently via malicious prompts, shared conversations, or custom GPTs without appearing in the victim's visible response.