Research

121 reports

All LLM Security Agentic AI Industry News Research Supply Chain Prompt Injection First Look: Security Regulatory Jailbreaks Adversarial ML Data Poisoning Model Theft AI Security Tools Security Operations

AI Worm With Embedded LLM Enables Self-Propagation

ATLAS OWASP HIGH ▲ 7.5 Schneier on Security Jun 08, 2026

Researchers have prototyped an internet worm that bundles its own large language model, executing it on compromised hosts to enable fully decentralised propagation with no single point of control. The design mirrors John Brunner's 1975 fictional conception of a worm and echoes the destructive potential of WannaCry and NotPetya, but with the added capability of dynamically generating novel attacks by ingesting recent public vulnerability disclosures. The absence of a command-and-control chokepoint makes traditional takedown strategies ineffective, significantly raising the threat posed by AI-augmented malware.

Google Gemini Android Hijacked by Indirect Prompt Injection

ATLAS OWASP HIGH ▲ 9.1 The Hacker News Jun 04, 2026

SafeBreach researcher Or Yair demonstrated that malicious text embedded in WhatsApp, Slack, SMS, or Signal notifications could trigger indirect prompt injection against Google Gemini's Android Utilities feature, causing the assistant to execute real device actions without user awareness. A novel bypass technique called 'Fake Context Alignment' defeated Google's post-patch authorization checks by exploiting multilingual obfuscation and muted hyperlinks to trick victims into authorising sensitive actions. Google has patched the issue, but the research exposes a fundamentally large attack surface where any app capable of pushing a notification becomes a potential injection vector.

Adversa AI: 89% of AI Agents Fail Security Tests

ATLAS OWASP HIGH ▲ 8.2 SecurityWeek Jun 04, 2026

Adversa AI's AI Risk Quadrant report evaluated 100 AI agents across ten categories, finding that only 11 qualify as both capable and well-defended. The research identifies a structural 'power-protection inversion' where the most capable agents also present the widest attack surface, driven by a 'lethal trifecta' of private data access, exposure to untrusted content, and outbound action capability. Computer and coding agents showed the most severe exposure, raising urgent concerns about autonomous agent deployment in enterprise environments.

Claude Sandbox Escape Enables Credential Exfiltration

ATLAS OWASP MEDIUM ▲ 7.2 Simon Willison May 31, 2026

Anthropic has published detailed documentation of its sandboxing architecture across Claude.ai, Claude Code, and Claude Cowork, including disclosure of a previously identified credential exfiltration vector via the api.anthropic.com/v1/files endpoint. The writeup covers process-level isolation technologies including gVisor, Seatbelt, Bubblewrap, and full VM approaches, and candidly acknowledges security gaps that were missed. This transparency is notable for the agentic AI space, where sandbox documentation is typically sparse and trust is difficult to calibrate.

ChatGPT Markdown Injection Enables Phishing in Web Summarizer

ATLAS OWASP HIGH ▲ 8.5 The Hacker News May 31, 2026

Permiso Security has disclosed ChatGPhish, a vulnerability in ChatGPT's web summarisation feature that allows attacker-controlled Markdown payloads embedded in third-party pages to render phishing links, spoofed alerts, and QR codes directly within ChatGPT's trusted UI. The attack requires no user interaction beyond asking ChatGPT to summarise a malicious page, and can exfiltrate IP addresses, User-Agent strings, and Referer headers via auto-fetched remote images. The technique significantly expands the phishing attack surface beyond email into everyday AI-assisted browsing workflows, posing a particular risk in enterprise environments.

CogCAPTCHA30 Fingerprints AI Agents via Behavioral Analysis

ATLAS OWASP MEDIUM ▲ 6.5 HN AI Security May 31, 2026

Researchers have developed CogCAPTCHA30, a 30-task cognitive battery demonstrating that AI agents (GPT, Claude, Gemini) solve CAPTCHAs with statistically distinguishable behavioural patterns despite matching human accuracy. The study introduces a 'Process Turing Test' concept, showing output equivalence and process equivalence are uncorrelated — meaning AI agents can be detected not by what they answer, but by how they answer. This has direct implications for bot detection, anti-automation defences, and the arms race between AI-driven agents and human-verification systems.

FuzzingBrain V2 Discovers 29 Zero-Day Vulnerabilities

ATLAS OWASP HIGH ▲ 7.8 HN AI Security May 29, 2026

Researchers have developed FuzzingBrain V2, a multi-agent LLM system capable of autonomously discovering and reproducing software vulnerabilities with a 90% detection rate on a competitive benchmark dataset. The system discovered 29 zero-day vulnerabilities across 12 open-source projects, all confirmed by maintainers, raising both defensive and dual-use concerns for the security community. While positioned as a defensive research tool, the automation of end-to-end vulnerability discovery at this scale represents a meaningful shift in the offensive capability landscape.

GreyVibe Deploys ChatGPT and Gemini in LLM Attack Chain

ATLAS OWASP HIGH ▲ 7.5 SecurityWeek May 29, 2026

WithSecure has documented GreyVibe, a Russia-nexus threat actor systematically deploying ChatGPT, Google Gemini, and Ideogram AI across every phase of its attack chain — from phishing lure creation to custom malware development — against Ukrainian targets since August 2025. The group's LLM-assisted malware, LegionRelay, contained design flaws introduced during AI-generated development, which paradoxically allowed researchers to track the group over an extended period. The case illustrates both the operational leverage AI provides to moderately skilled threat actors and the novel forensic signatures that AI-assisted development can inadvertently introduce.

GreyVibe Uses ChatGPT and Gemini for Ukraine Cyberespionage

ATLAS OWASP HIGH ▲ 7.5 BleepingComputer May 29, 2026

A likely Russian threat group dubbed GreyVibe has been actively using commercial LLMs — including ChatGPT and Google Gemini — to generate high-quality phishing lures, malware tooling, and social-engineering content targeting Ukrainian military, government, and civilian organisations. WithSecure researchers identified LLM artefact markers embedded in campaign imagery, confirming AI-assisted content generation at scale. The case represents a concrete, documented example of adversarial LLM weaponisation in an active nation-state-adjacent cyberespionage campaign.

SQLite Blocks AI-Generated Code Contributions

ATLAS OWASP MEDIUM ▲ 6.2 Simon Willison May 29, 2026

SQLite has formally prohibited agentic code contributions and strengthened its policy language, reflecting growing concern over AI-generated submissions overwhelming open source maintainers. The project was forced to create a separate bug forum after being flooded with AI-generated reports of inconsistent quality. This represents an emerging operational security challenge for critical infrastructure software projects targeted by autonomous AI coding agents.

AI Supply Chain Compromise: Models Lack Bill of Materials

ATLAS OWASP MEDIUM ▲ 6.2 Dark Reading May 25, 2026

As AI systems proliferate across enterprise environments, the lack of standardised AI Bills of Materials (AI BOMs) leaves organisations blind to the components, training data, and dependencies embedded in deployed models. The article examines whether 2026 marks a turning point for AI BOM adoption as a risk management practice. Without visibility into AI supply chains, organisations remain exposed to hidden vulnerabilities including poisoned models, compromised dependencies, and undisclosed third-party components.

CVE-2026-5194: Anthropic Claude Discovers 10,000+ Flaws

ATLAS OWASP HIGH ▲ 8.5 The Hacker News May 25, 2026

Anthropic's Project Glasswing has deployed Claude Mythos Preview — a frontier AI model — to autonomously discover over 10,000 high- and critical-severity vulnerabilities across widely used open-source software, with 1,094 confirmed as valid high/critical flaws. The initiative highlights a growing asymmetry: AI is accelerating vulnerability discovery far faster than the security community can remediate, compressing patch windows and raising the stakes for defenders. Anthropic is now urging shorter patch cycles and hardened defaults, warning that comparable offensive capabilities could soon be broadly accessible to threat actors.

Constraint Decay: LLM Code Agents Fail at Scale

ATLAS OWASP HIGH ▲ 7.2 HN AI Security May 25, 2026

A systematic study of LLM agents performing backend code generation reveals a 'constraint decay' phenomenon where agents lose up to 30 assertion pass-rate points as structural requirements accumulate, approaching complete failure in some configurations. This fragility has direct security implications: production deployments relying on LLM-generated code may silently violate architectural constraints such as ORM patterns, database access controls, and API contracts. The findings expose a critical gap between functional correctness and structural safety in agentic coding systems.

LLM Safety Benchmarks Fail to Reliably Measure Security

ATLAS OWASP MEDIUM ▲ 6.2 Schneier on Security May 22, 2026

A report highlighted by Bruce Schneier argues that AI security cannot be reliably measured through benchmarks alone, drawing parallels to the decades-long evolution of software security engineering. The core finding is that LLM weight spaces encode continuous spectrums that resist meaningful quantitative measurement, making trust in model outputs structurally difficult to establish. The practical implication is that organisations must rely on assurance processes rather than scorecards to manage AI security risk.

Mythos AI Exploits macOS Kernel Memory Corruption

ATLAS OWASP HIGH ▲ 7.5 Schneier on Security May 22, 2026

A threat group leveraged Anthropic's Mythos AI model to identify and exploit a kernel memory corruption vulnerability in Apple's M5 chip running macOS. This represents a concrete, reported instance of AI-assisted vulnerability research being used offensively to discover low-level hardware-adjacent exploits. The incident underscores the dual-use danger of increasingly capable AI coding and reasoning models in the hands of adversarial actors.

Research

Stay ahead of the threat.