Researcher

149 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

LLM Agents Exploit Human Over-Trust in Strategic Games

ATLAS OWASP MEDIUM ▲ 6.2 Schneier on Security Apr 17, 2026

Research published via Schneier on Security reveals that humans systematically over-trust LLMs in strategic game environments, defaulting to Nash-equilibrium rational play based on assumptions of LLM rationality and cooperation. This behavioural bias has direct security implications for mixed human-LLM systems, where adversaries could exploit predictable human over-trust to manipulate decision outcomes. The findings underscore systemic risks in deploying LLMs as agents in high-stakes economic or security-relevant decision loops.

Agentic AI Excessive Agency Bypasses Security Testing

ATLAS OWASP MEDIUM ▲ 6.5 The Hacker News Apr 16, 2026

The article examines the architectural tension between fully agentic AI systems and deterministic validation frameworks in security testing contexts, arguing that unconstrained AI autonomy introduces repeatability and auditability risks. It highlights how probabilistic AI behaviour — while valuable for exploration — undermines the measurable, consistent outcomes required for enterprise security validation programs. The piece reflects a broader industry debate about governing AI agency in high-stakes operational environments.

Anthropic MCP Supply Chain Flaw Enables Command Injection

ATLAS OWASP CRITICAL ▲ 9.1 SecurityWeek Apr 16, 2026

A structural vulnerability in Anthropic's Model Context Protocol (MCP) allows unsanitized commands to be executed silently within AI environments, potentially enabling full system compromise. Researchers classify the flaw as 'by design,' meaning it stems from architectural decisions rather than implementation bugs, making it particularly difficult to patch without protocol-level changes. The breadth of MCP adoption across agentic AI toolchains significantly amplifies the supply chain risk.

AI Agent Prompt Injection and Data Leakage Threats Rise

ATLAS OWASP MEDIUM ▲ 6.5 SecurityWeek Apr 16, 2026

Capsule Security, an Israeli startup, has emerged from stealth with $7 million in seed funding focused on runtime security for AI agents, continuously monitoring their behaviour to detect and prevent unsafe or malicious actions. This positions the company within the rapidly growing agentic AI security space, where autonomous agents executing actions on behalf of users represent a significant and underexplored attack surface. The funding signals growing investor recognition of the risks posed by unmonitored AI agent behaviour, including prompt injection, excessive agency, and unintended tool use.

Prompt Injection Flaws in Salesforce and Microsoft AI

ATLAS OWASP HIGH ▲ 8.2 Dark Reading Apr 16, 2026

Prompt injection vulnerabilities in Salesforce Agentforce and Microsoft Copilot were patched after researchers demonstrated that external attackers could exploit them to exfiltrate sensitive user data. The flaws highlight systemic risks in enterprise AI agent deployments, where insufficient input sanitisation allows malicious content to hijack agent behaviour. Both vendors have issued patches, but the incidents underscore the growing attack surface introduced by agentic AI systems operating with elevated privileges.

Claude Code Source Leak Exposes 512K Lines of Code

ATLAS OWASP MEDIUM ▲ 6.2 HN AI Security Apr 16, 2026

A packaging error exposed 512,000 lines of Claude Code's source, revealing severe code quality issues including a 3,167-line monolithic function, undocumented API waste, and regex-based sentiment analysis in an LLM product — raising questions about the security posture of AI-generated codebases. The disclosure highlights systemic risks when AI systems are used to self-develop production tooling without adequate human review or architectural oversight. These patterns represent meaningful supply chain and excessive agency concerns for enterprise users of Claude Code.

GPT-5.4-Cyber Jailbreak and Prompt Injection Risks

ATLAS OWASP HIGH ▲ 7.2 The Hacker News Apr 15, 2026

OpenAI has launched GPT-5.4-Cyber, a cybersecurity-optimised model variant, alongside an expanded Trusted Access for Cyber (TAC) programme targeting authenticated defenders and security teams. While the initiative is framed as a defensive measure, the dual-use nature of a vulnerability-detection model introduces significant risk of adversarial inversion — where threat actors could exploit the same capabilities to discover and weaponise unpatched vulnerabilities at scale. OpenAI acknowledges this risk and states it is iteratively strengthening safeguards against jailbreaks and adversarial prompt injection as access broadens.

Anthropic Claude Mythos Sparks AI Vulnerability Storm Warning

ATLAS OWASP HIGH ▲ 7.2 Dark Reading Apr 14, 2026

The Cloud Security Alliance has issued a warning about an anticipated 'AI vulnerability storm' following the release of Anthropic's Claude Mythos model, urging CISOs to prepare defensive postures in advance of expected exploit activity. The advisory signals growing institutional concern that major LLM releases create systemic risk windows as adversaries probe new model capabilities and attack surfaces. Security leaders are being advised to treat post-release periods of frontier AI models as high-alert intervals requiring elevated monitoring and response readiness.

GenAI Security Risks: OWASP Updates LLM Top 10 Framework

ATLAS OWASP MEDIUM ▲ 7.2 Dark Reading Apr 14, 2026

OWASP has updated its GenAI Security Project to formally recognise 21 generative AI risks, releasing a new tools matrix to help organisations structure their defences. The update notably distinguishes between securing traditional GenAI systems and the emerging attack surface presented by agentic AI architectures. This guidance represents a significant standards-level acknowledgement that agentic AI requires its own dedicated security posture.

Google Vertex AI Over-Privilege Enables Data Exfiltration

ATLAS OWASP HIGH ▲ 8.5 Dark Reading Apr 13, 2026

Palo Alto Networks researchers have identified over-privilege vulnerabilities in Google's Vertex AI platform, demonstrating how malicious actors could exploit AI agents to exfiltrate sensitive data and pivot into restricted cloud infrastructure. The findings highlight systemic risks in agentic AI deployments where excessive permissions granted to AI workloads expand the attack surface beyond traditional cloud security boundaries. This research underscores the growing urgency around securing AI agent permissions and enforcing least-privilege principles in enterprise ML platforms.

SWE-bench, WebArena Exploited via Environmental Manipulation

ATLAS OWASP CRITICAL ▲ 9.2 HN AI Security Apr 11, 2026

Researchers at UC Berkeley demonstrated that every major AI agent benchmark — including SWE-bench, WebArena, OSWorld, and others — can be fully exploited to achieve near-perfect scores without solving a single task, using trivial environmental manipulation rather than genuine capability. The attacks include pytest hook injection, config file leakage, DOM manipulation, and reward component bypassing, with zero LLM calls required in most cases. This represents a systemic integrity failure in the evaluation infrastructure underpinning AI deployment decisions across industry and research.

US summons bank bosses over cyber risks from Anthropic's latest AI model

ATLAS OWASP CRITICAL ▲ 8.5 HN AI Security Apr 10, 2026

The US Treasury convened major bank executives to discuss cybersecurity risks posed by Anthropic's unreleased Claude Mythos model, which the company claims has surpassed nearly all human experts at finding and exploiting software vulnerabilities. A code leak prompted Anthropic to publicly acknowledge the model's unprecedented offensive cyber capability, raising systemic financial sector risk concerns. The meeting signals growing regulatory awareness of AI-enabled cyber threats to critical financial infrastructure.

Anthropic Mythos AI Autonomously Discovers Zero-Day Exploits

ATLAS OWASP HIGH ▲ 8.2 Dark Reading Apr 10, 2026

Anthropic has released a preview of 'Mythos,' an AI model reportedly capable of autonomously discovering and exploiting critical zero-day vulnerabilities, raising significant dual-use concerns. While Anthropic claims the model ships with access controls, the security community is scrutinising whether those safeguards are sufficient to prevent misuse by malicious actors. The development represents a pivotal moment in the arms race between offensive AI capabilities and defensive governance frameworks.

botctl Process Manager Enables Prompt Injection Attacks

ATLAS OWASP HIGH ▲ 7.2 HN AI Security Apr 09, 2026

botctl is an open-source process manager that enables persistent, autonomous AI agents (currently Claude-backed) to run continuously as background daemons with tool access, file system write permissions, and internet connectivity. While marketed as a productivity tool, the architecture introduces substantial attack surface through unattended agentic execution, a skills marketplace with third-party prompt injection, and a locally-exposed web dashboard. The combination of persistent autonomy, extensible skill modules from arbitrary GitHub repositories, and session memory creates compounding risk vectors relevant to agentic AI security.

Researcher

Stay ahead of the threat.