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

Microsoft RAMPART Tests AI Agents for Prompt Injection

ATLAS OWASP MEDIUM ▲ 7.2 The Hacker News May 22, 2026

Microsoft has released two open-source tools, RAMPART and Clarity, aimed at embedding security testing into AI agent development workflows. RAMPART extends the existing PyRIT framework with a Pytest-native harness for running adversarial and safety tests against AI agents, explicitly covering cross-prompt injection, data exfiltration, and behavioural regression scenarios. Clarity operates as a pre-code design analysis tool, helping teams surface and challenge unsafe assumptions before an agentic system is built.

DeepSeek Activation Steering Enables Local LLM Jailbreak

ATLAS OWASP MEDIUM ▲ 6.2 HN AI Security May 17, 2026

Activation steering — the technique of directly manipulating LLM internal representations mid-inference to alter model behaviour — is becoming more accessible to non-lab engineers via local models like DeepSeek-V4-Flash. This democratisation lowers the barrier for adversaries to craft targeted behavioural overrides that bypass prompt-level safety controls. The emergence of first-class steering support in tools like DwarfStar 4 signals that model-internal manipulation is transitioning from academic curiosity to practical attack surface.

CVE-2026-44112: OpenClaw Sandbox Escape and RCE

ATLAS OWASP CRITICAL ▲ 8.9 The Hacker News May 15, 2026

Researchers at Cyera disclosed four vulnerabilities in OpenClaw, an AI agent runtime platform, that can be chained to achieve credential theft, privilege escalation, and persistent backdoor access. The attack chain, dubbed 'Claw Chain', exploits sandbox escapes, allowlist bypasses, and a spoofable ownership flag in the MCP loopback runtime to weaponise the agent's own privileges against the host environment. All four CVEs have been patched in OpenClaw version 2026.4.22 and users should update immediately.

Agent Hijacking: Microsoft's Defense-in-Depth Framework

ATLAS OWASP MEDIUM ▲ 7.2 Microsoft Security Blog May 15, 2026

Microsoft's Security Blog introduces a layered defense-in-depth model specifically designed for autonomous AI agents, which now invoke tools, modify data, and trigger workflows with minimal human oversight. The framework identifies novel threat classes — including agent hijacking, intent breaking, and supply chain compromise — that are amplified by agentic autonomy. The guidance positions application-layer architecture, permissions, and governance as the most critical controls as agent autonomy scales.

Sweet Security Launches Sweet Attack Agentic AI Red Teaming

ATLAS OWASP MEDIUM ▲ 7.2 SecurityWeek May 14, 2026

Sweet Security has launched 'Sweet Attack', a continuous agentic AI red teaming platform designed to counter the growing asymmetry between AI-assisted attackers and human defenders — a tipping point the industry has termed the 'Mythos Moment'. The platform differentiates itself by grounding frontier model reasoning in live runtime telemetry from each customer's own environment, including topology, identity paths, and unencrypted Layer 7 exposure, to identify genuinely exploitable attack chains rather than theoretical ones. The development signals a broader industry shift toward autonomous, environment-aware AI agents as a necessary component of modern security operations.

GPT-5.5 and Claude Mythos Lower Barriers to Offensive AI

ATLAS OWASP HIGH ▲ 7.2 Schneier on Security May 14, 2026

The UK AI Security Institute has evaluated GPT-5.5 and found it comparable to Claude Mythos in identifying security vulnerabilities, with both models now generally available to the public. This parity raises serious concerns about the lowered barrier to entry for offensive cyber operations, as adversaries can leverage widely accessible models for vulnerability research. Commentary from security experts highlights that LLM-based vulnerability discovery is constrained to known attack patterns, but the existence of jailbreaks means guardrails provide only partial mitigation.

Microsoft MDASH Discovers 16 Windows RCE Flaws

ATLAS OWASP HIGH ▲ 7.8 The Hacker News May 14, 2026

Microsoft has disclosed MDASH, a multi-model agentic AI scanning system that autonomously discovered 16 vulnerabilities patched in May 2026's Patch Tuesday, including two critical RCE flaws. The system orchestrates over 100 specialised AI agents in a structured pipeline covering auditing, debating, and proof-of-exploitability stages. MDASH represents a significant shift in how AI is being deployed offensively and defensively within the vulnerability research lifecycle, with direct implications for how agentic AI systems are trusted, scoped, and governed.

OpenAI Daybreak Vulnerability Detection Enables LLM Jailbreak

ATLAS OWASP MEDIUM ▲ 7.2 The Hacker News May 13, 2026

OpenAI has launched Daybreak, an AI-powered cybersecurity platform combining GPT-5.5 variants and Codex Security to automate vulnerability detection, threat modelling, and patch validation for enterprise codebases. The initiative introduces a tiered model access structure — including a permissive 'GPT-5.5-Cyber' for red teaming — raising questions about dual-use risk and model misuse if access controls are circumvented. The rollout also contextualises a broader industry tension: AI is accelerating vulnerability discovery faster than defenders can remediate, contributing to triage fatigue and hallucinated bug reports.

Excessive Agency in AI Agents: Tool Access Control Gaps

ATLAS OWASP LOW ▲ 6.2 HN AI Security May 13, 2026

Statewright is an open-source framework that enforces state machine constraints on AI agents, restricting which tools agents can invoke during each phase of a workflow. The project directly addresses the Excessive Agency problem, where AI agents operating with broad, unconstrained tool access can take unintended or harmful actions. While a defensive development rather than a threat disclosure, it signals growing practitioner awareness of agentic AI risk and offers a concrete mitigation pattern for teams deploying coding agents like Claude Code, Codex, or Cursor.

AI-Powered Exploit Development by Threat Actors

ATLAS OWASP HIGH ▲ 7.2 Dark Reading May 12, 2026

Threat actors are now actively deploying large language models to accelerate exploit development and automate complex cyberattack workflows, marking a significant evolution in adversarial tooling. This shift lowers the technical barrier for sophisticated attack execution, enabling less-skilled actors to produce functional exploits at scale. The trend signals a structural change in the offensive threat landscape, with AI acting as a force multiplier for adversaries.

PromptSpy Zero-Day: AI-Generated Malware for Mass Exploitation

ATLAS OWASP CRITICAL ▲ 9.2 Mandiant Blog May 12, 2026

Google's Threat Intelligence Group (GTIG) has identified, for the first time, a criminal threat actor using a zero-day exploit believed to have been AI-generated, intended for mass exploitation before proactive counter-discovery intervened. The report also documents AI-augmented malware development, autonomous attack orchestration via AI-enabled malware (PROMPTSPY), and obfuscated LLM access pipelines used by adversaries to bypass usage controls. Nation-state actors from China and North Korea are actively pursuing AI-assisted vulnerability discovery, marking a significant escalation in adversarial AI capability.

AI-Generated Zero-Day: 2FA Bypass in Web Admin Tool

ATLAS OWASP CRITICAL ▲ 9.2 The Hacker News May 12, 2026

Google's Threat Intelligence Group has confirmed the first known instance of a threat actor using an AI model to discover and weaponize a zero-day vulnerability — a 2FA bypass in a popular open-source web administration tool. The exploit, delivered via a Python script bearing hallmarks of LLM-generated code (including hallucinated CVSS scores and structured docstrings), was designed for mass exploitation. This marks a significant inflection point in the offensive AI threat landscape, demonstrating that AI-assisted vulnerability discovery and weaponization has moved from theoretical risk to confirmed operational reality.

Steganography in LLMs Enables Covert Data Exfiltration

ATLAS OWASP MEDIUM ▲ 6.5 Schneier on Security May 12, 2026

Research highlighted by Bruce Schneier confirms that LLMs are highly effective at embedding hidden messages within seemingly normal text, a technique known as text-in-text steganography. This capability raises significant concerns for covert communications, data exfiltration, and the evasion of AI content moderation systems. Even small models with ~4 billion parameters demonstrate robust encoding and decoding of obfuscated language, lowering the barrier for adversarial misuse.

Claude Chrome Extension Prompt Injection Enables Agent Takeover

ATLAS OWASP HIGH ▲ 9.1 SecurityWeek May 09, 2026

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.

Firefox Vulnerabilities Discovered via AI-Assisted Fuzzing

ATLAS OWASP HIGH ▲ 7.2 Simon Willison May 08, 2026

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.

Research

Stay ahead of the threat.