Agentic AI

194 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

Anthropic Model Exploits Zero-Days Faster Than SOC Response

ATLAS OWASP HIGH ▲ 7.2 The Hacker News Apr 14, 2026

The article highlights a critical operational gap in SOC environments where AI-accelerated adversarial capabilities — including an Anthropic model restricted after autonomously exploiting zero-day vulnerabilities — are outpacing defender response workflows. While detection times (MTTD) have improved, the post-alert investigation window remains the primary exposure point, with breakout times of 29 minutes and adversary hand-off times collapsing to 22 seconds. The piece argues that AI-driven investigation tooling is the necessary counter to compress this post-alert gap.

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.

CVE-2025-59528: Flowise RCE Exploited Across 12,000 Instances

ATLAS OWASP CRITICAL ▲ 9.4 The Hacker News Apr 13, 2026

A maximum-severity (CVSS 10.0) remote code execution vulnerability in Flowise, a widely-used open-source AI agent builder, is under active exploitation with over 12,000 internet-exposed instances at risk. The flaw, CVE-2025-59528, exists in the CustomMCP node and allows unauthenticated JavaScript execution with full Node.js runtime privileges via unsanitised MCP server configuration input. This marks the third Flowise vulnerability exploited in the wild, underscoring systemic security gaps in AI orchestration and agent-building 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.

Anthropic Claude Prompt Injection Enables Excessive Agency

ATLAS OWASP LOW ▲ 6.2 CrowdStrike Blog Apr 11, 2026

CrowdStrike, as a founding member of Anthropic's Mythos program, is highlighting the security challenges posed by increasingly capable frontier AI models, signaling a growing industry focus on securing agentic and large-scale AI systems. The article underscores the philosophical and practical position that AI capability gains must be matched by proportional security investment. While the piece is primarily a vendor partnership announcement and executive viewpoint, it reflects an important industry trend toward formalising AI-specific security frameworks and tooling.

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.

AI Browser Extensions 60% Riskier Than Standard Tools

ATLAS OWASP HIGH ▲ 7.5 The Hacker News Apr 10, 2026

A LayerX report reveals that AI browser extensions represent a largely unmonitored attack surface in enterprise environments, with 1-in-6 enterprise users already running at least one AI extension. These extensions are statistically riskier than standard extensions — 60% more likely to carry a CVE, 3x more likely to access cookies, and capable of exfiltrating sensitive data without triggering DLP or SaaS monitoring controls. The finding highlights a critical governance gap in AI consumption channels that bypasses traditional enterprise security tooling.

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.

GitHub Supply Chain Attacks via PRT-scan Campaign

ATLAS OWASP HIGH ▲ 7.5 Dark Reading Apr 06, 2026

A threat actor identified as part of the PRT-scan campaign has leveraged AI-assisted automation to systematically target a widespread GitHub misconfiguration, marking the second such campaign in recent months. The use of AI for automated reconnaissance and exploitation of supply chain vulnerabilities represents a significant escalation in attacker capability. This campaign highlights the growing risk of AI-augmented attacks against software supply chains, which can have cascading downstream effects on ML pipelines and production systems.

CrowdStrike Charlotte AI Vulnerable to Prompt Injection

ATLAS OWASP MEDIUM ▲ 6.5 CrowdStrike Blog Apr 06, 2026

CrowdStrike's Charlotte AI AgentWorks introduces an agentic security ecosystem where autonomous AI agents collaborate to perform security operations tasks with reduced human intervention. The platform raises important considerations around excessive agency, trust boundaries between agents, and the attack surface introduced by interconnected AI systems in security-critical environments. As agentic SOC architectures proliferate, the security of the AI agents themselves becomes a primary concern.

Shadow AI Governance Threats Across SaaS and Cloud Endpoints

ATLAS OWASP MEDIUM ▲ 6.5 CrowdStrike Blog Apr 06, 2026

CrowdStrike has announced new platform innovations targeting the governance of Shadow AI and the security of AI agents across endpoints, SaaS, and cloud environments. The release highlights growing enterprise concerns around unmanaged AI tool proliferation and the attack surface introduced by autonomous AI agents. These developments reflect an industry-wide shift toward operationalising AI-specific security controls within existing SOC workflows.

Agentic AI

Stay ahead of the threat.