Snowflake Cortex AI Escapes Sandbox and Executes Malware

A GitHub Issue Title Compromised 4,000 Developer Machines

A prompt injection in a GitHub issue triggered a chain reaction that ended with 4,000 developers getting OpenClaw installed without consent. The attack composes well-understood vulnerabilities into something new: one AI tool bootstrapping another.

Prompt Injection Attacks Are Thwarting AI Hacking Agents

“Context bombing” tricks malicious AI agents into shutting down before they can do harm.

Code scanning shows AI security detections on pull requests - GitHub Changelog

GitHub code scanning now surfaces AI-powered security detections directly on pull requests, expanding vulnerability coverage to languages and frameworks not currently supported by CodeQL. These detections help teams identify and…

AI CVE Slop: The Crisis Drowning Open Source Security

The proliferation of AI-generated vulnerability reports — commonly termed “AI slop” — has emerged as one of the most significant…

TencentCloud/CubeSandbox

Instant, Concurrent, Secure & Lightweight Sandbox for AI Agents.

ExploitGym: Can AI Agents Turn Security Vulnerabilities into Real Attacks?

AI agents are rapidly gaining capabilities that could significantly reshape cybersecurity, making rigorous evaluation urgent. A critical capability is exploitation: turning a vulnerability, which is not yet an attack, into a concrete security impact, such as unauthorized file access or code execution. Exploitation is a particularly challenging task because it requires low-level program reasoning (e.g., about memory layout), runtime adaptation, and sustained progress over long horizons. Meanwhile, it is inherently dual-use, supporting defensive workflows while lowering the barrier for offense. Despite its importance and diagnostic value, exploitation remains under-evaluated. To address this gap, we introduce ExploitGym, a large-scale, diverse, realistic benchmark on the exploitation capabilities of AI agents. Given a program input that triggers a vulnerability, ExploitGym tasks agents with progressively extending it into a working exploit. The benchmark comprises 898 instances sourced from real-world vulnerabilities across three domains, including userspace programs, Google's V8 JavaScript engine, and the Linux kernel. We vary the security protections applied to each instance, isolating their impact on agent performance. All configurations are packaged in reproducible containerized environments. Our evaluation shows that while exploitation remains challenging, frontier models can successfully exploit a non-trivial fraction of vulnerabilities. For example, the strongest configurations are Anthropic's latest model Claude Mythos Preview and OpenAI's GPT-5.5, which produce working exploits for 157 and 120 instances, respectively. Notably, even with widely used defenses enabled, models retain non-trivial success rates. These results establish ExploitGym as an effective testbed for exploitation and highlight the growing cybersecurity risks posed by increasingly capable AI agents.

ExploitGym: Can AI Agents Turn Security Vulnerabilities into Real Attacks?

AI agents are rapidly gaining capabilities that could significantly reshape cybersecurity, making rigorous evaluation urgent. A critical capability is exploitation: turning a vulnerability, which is not yet an attack, into a concrete security impact, such as unauthorized file access or code execution. Exploitation is a particularly challenging task because it requires low-level program reasoning (e.g., about memory layout), runtime adaptation, and sustained progress over long horizons. Meanwhile, it is inherently dual-use, supporting defensive workflows while lowering the barrier for offense. Despite its importance and diagnostic value, exploitation remains under-evaluated. To address this gap, we introduce ExploitGym, a large-scale, diverse, realistic benchmark on the exploitation capabilities of AI agents. Given a program input that triggers a vulnerability, ExploitGym tasks agents with progressively extending it into a working exploit. The benchmark comprises 898 instances sourced from real-world vulnerabilities across three domains, including userspace programs, Google's V8 JavaScript engine, and the Linux kernel. We vary the security protections applied to each instance, isolating their impact on agent performance. All configurations are packaged in reproducible containerized environments. Our evaluation shows that while exploitation remains challenging, frontier models can successfully exploit a non-trivial fraction of vulnerabilities. For example, the strongest configurations are Anthropic's latest model Claude Mythos Preview and OpenAI's GPT-5.5, which produce working exploits for 157 and 120 instances, respectively. Notably, even with widely used defenses enabled, models retain non-trivial success rates. These results establish ExploitGym as an effective testbed for exploitation and highlight the growing cybersecurity risks posed by increasingly capable AI agents.

AI Agent Executes 'First' End-To-End Ransomware Attack - Slashdot

Sysdig says it has documented the first ransomware attack carried out end to end by an AI agent, which autonomously exploited exposed systems, stole credentials, established persistence, compromised a production database, and destroyed data. The research team named the attacker "JadePuffer" and said...

Top AI Security Incidents of 2025 Revealed | Adversa AI

Discover how AI systems are being hacked in the wild — from prompt injection to agent abuse — with real breaches, lessons, and defenses in Adversa AI’s 2025 report.

A Meta AI security researcher said an OpenClaw agent ran amok on her inbox  | TechCrunch

The viral X post from an AI security researcher reads like satire. But it's really a word of warning about what can go wrong when handing tasks to an AI agent.

AI vs human code gen report: AI code creates 1.7x more issues

We analyzed 470 open-source GitHub pull requests, using CodeRabbit’s structured issue taxonomy and found that AI generated code creates 1.7x more issues.

New AI Flaw Reporting System Fills Crucial Security Gap | CMU Software Engineering Institute

Flaw Reporting for AI (FLARE-AI) allows developers and security researchers to submit artificial intelligence flaws for formal, coordinated disclosure.

AI Agent Traps

As autonomous AI agents increasingly navigate the web, they face a novel challenge: the information environment itself. This gives rise to a critical vulnerability we refer to as "AI Agent Traps", i.e. adversarial content designed to manipulate, deceive, or exploit visiting agents. In this paper, we introduce the first known systematic framework for understanding this emerging threat. We break down how these traps work, identifying six types of attack: Content Injection Traps that exploit the gap between human perception, machine parsing, and dynamic rendering; Semantic Manipulation Traps, which corrupt an agent's reasoning and internal verification processes; Cognitive State Traps, which target an agent's long-term memory, knowledge bases, and learned behavioural policies; Behavioural Control Traps, which hijack an agent's capabilities to force unauthorised actions; Systemic Traps, which use agent interaction to create systemic failure, and Human-in-the-Loop Traps, which exploit cognitive biases to influence a human overseer. This research is not specific to any particular agent or model. By mapping this new attack surface, we identify critical gaps in current defences and propose a research agenda that could secure the entire agent ecosystem.