Every article scored, classified, and mapped to MITRE ATLAS and OWASP LLM Top 10 — so you always know what matters and why.
AI security intelligence analysis for 2026-W35 — MITRE ATLAS technique trends, OWASP LLM risk distribution, threat actor activity, and enterprise readiness assessment based on 25 articles.
Read full analysis →
A malicious Hugging Face repository impersonated OpenAI's legitimate Privacy Filter model, cloning its description verbatim to gain credibility and reach the platform's trending list with 244,000 downloads. The repository delivered a multi-stage attack chain culminating in a Rust-based information stealer targeting browser credentials, cryptocurrency wallets, and Discord data on Windows machines. The attack leveraged a dead-drop resolver pattern via a public JSON paste service, allowing operators to swap payloads without modifying the repository itself.
A malicious Hugging Face repository impersonating OpenAI's 'Privacy Filter' project reached #1 on the platform's trending list and accumulated 244,000 downloads before removal, delivering a multi-stage infostealer to Windows users. The attack chain used a disguised Python loader to execute PowerShell commands, ultimately deploying a Rust-based payload capable of harvesting browser credentials, crypto wallets, SSH/VPN configs, and screenshots. The campaign highlights the growing risk of AI/ML supply chain attacks through trusted model-sharing platforms.
A vulnerability dubbed ClaudeBleed in Anthropic's Claude Chrome extension allows any browser extension to inject arbitrary prompts into the Claude AI agent by exploiting lax permission checks and improper trust validation. Attackers can bypass user confirmation protections via DOM manipulation and repeated message forging, enabling full agent takeover for information theft or unauthorized actions. The flaw effectively breaks Chrome's extension security model and exposes users running Claude's agentic capabilities to third-party extension compromise.
Mozilla used early access to Anthropic's Claude Mythos model to systematically discover and patch hundreds of previously unknown vulnerabilities in Firefox, including bugs over 15–20 years old. The effort demonstrates a step-change in AI-assisted vulnerability research, with April 2026 seeing 423 security fixes compared to a monthly baseline of 20–30. The same capability that empowered Mozilla's defenders also signals that adversaries with similar model access could industrialise exploit discovery against open-source software at scale.
Threat actors created a convincing fake website impersonating Anthropic's Claude AI to trick developers into downloading a trojanized installer that deploys the new 'Beagle' backdoor alongside a PlugX malware chain. The campaign specifically targets Claude-Code developers by advertising a fraudulent 'high-performance relay service,' suggesting deliberate targeting of the AI developer community. The attack leverages DLL sideloading via a legitimate signed G Data executable to evade detection while establishing persistent remote access.
A vulnerability class dubbed 'TrustFall' demonstrates that malicious code repositories can trigger arbitrary code execution in AI-assisted developer tools including Claude Code, Cursor CLI, Gemini CLI, and GitHub Copilot CLI, with little to no user interaction required. The attack surface stems from inadequate or easily dismissed warning dialogs that fail to surface the risk of executing untrusted repository content. Developers cloning or opening adversarial repositories are exposed to full host-level compromise through the elevated trust these AI coding agents place in repository-supplied context.
Mitiga Labs has disclosed a stealthy attack chain targeting Claude Code's MCP infrastructure, allowing adversaries to silently intercept OAuth tokens by redirecting MCP traffic through attacker-controlled infrastructure. The attack requires only the ability to install a malicious npm package, which modifies ~/.claude.json to insert a proxy and pre-sets trust flags to suppress security prompts. Because the OAuth token grants broad access to all connected SaaS tools, successful exploitation effectively hands attackers a persistent master key to the victim's integrated development environment.
Cisco's AI Threat Intelligence team has demonstrated that bounded pixel-level perturbations can recover the attack effectiveness of degraded typographic images against vision-language models (VLMs), enabling hidden prompt injection that bypasses both human review and content filters. The technique works by optimising perturbations against open-source embedding models and transferring results to proprietary systems like GPT-4o and Claude, exposing a cross-model transferability risk. The attack allows adversaries to embed instructions—such as data exfiltration commands—inside images that appear as visual noise to human observers.
Microsoft's Defender Security Research Team disclosed two CVEs in Semantic Kernel — a widely-used AI agent orchestration framework — demonstrating how prompt injection can escalate to remote code execution via compromised plugins. The vulnerabilities (CVE-2026-26030 and CVE-2026-25592) expose a systemic risk in the agentic AI layer: because frameworks like Semantic Kernel abstract tool orchestration, a single flaw in how LLM outputs are mapped to system tools can propagate across every application built on that foundation. This research signals a critical shift in AI threat modelling, where prompt injection is no longer a content risk but an execution risk.
Enterprises are deploying AI agents faster than governance frameworks can track them, creating a shadow identity layer that operates outside traditional IAM visibility. These agents run continuously, accumulate permissions opportunistically, and interact with sensitive data at machine speed — largely unmonitored. The structural gap between agent activity and IAM coverage represents a significant and growing attack surface for privilege abuse and data exfiltration.
A critical heap out-of-bounds read vulnerability (CVE-2026-7482, CVSS 9.3) in Ollama's GGUF model loader allows unauthenticated remote attackers to exfiltrate sensitive heap memory — including API keys, prompts, and PII — using just three API calls. With approximately 300,000 Ollama instances publicly exposed and no authentication required by default, the attack surface is immediately and broadly exploitable. The vulnerability has been patched in Ollama version 0.17.1, but unpatched internet-facing deployments remain at critical risk.
Joey Melo, Principal Security Researcher at CrowdStrike, outlines his methodology for AI red teaming, focusing on manipulating LLM guardrails through jailbreaking and data poisoning without altering underlying source code. His work, rooted in competitive AI hacking challenges, translates classical adversarial thinking into the emerging field of machine learning security. The profile highlights the growing professionalisation of AI red teaming as organisations seek to harden LLM deployments against real-world manipulation attacks.
A scan of over one million exposed AI services found pervasive security failures including absent authentication, leaked API keys, and exposed business logic across self-hosted LLM deployments. Agent management platforms such as Flowise and n8n were discovered internet-exposed without access controls, revealing credential lists and internal workflows. The findings indicate systemic misconfiguration risk as enterprises race to self-host AI infrastructure without applying baseline security practices.
A malicious version of PyTorch Lightning (v2.6.3) was published to PyPI, embedding a hidden execution chain that silently downloads a JavaScript runtime and executes a heavily obfuscated credential-stealing payload dubbed 'ShaiWorm'. The attack targeted AI/ML developers who use this popular deep learning framework, exposing cloud credentials, API keys, browser-stored secrets, and GitHub tokens. The package has since been reverted to a safe version, but any developer who imported the compromised version should rotate all secrets immediately.
The US Department of Defense has formalised agreements with seven major technology companies — including Google, Microsoft, OpenAI, and Amazon Web Services — to integrate AI into classified military networks for battlefield decision support. The move raises significant AI security concerns around human oversight, adversarial manipulation of high-stakes AI systems, and supply chain risks introduced by multiple commercial vendors operating within classified environments. Notably, Anthropic was excluded following a public dispute over AI safety and ethics in warfare.
◉ AI THREAT BRIEFING
Twice-weekly digest of critical AI security developments — every story mapped to MITRE ATLAS and OWASP LLM Top 10. Free.
No spam. Unsubscribe anytime.