Anthropic Expands Claude Access for Vetted Cyber Teams as Glasswing Finds 129,000 Flaws

Anthropic on Tuesday said it's expanding a program that allows vetted cybersecurity professionals to test its advanced artificial intelligence AI models with reduced safeguards and blocking classifiers, as the company claimed its Project Glasswing initiative uncovered at least 129,000 verified...

Anthropic and OpenAI Models Still Attempt Restricted Actions in Safety Tests

Anthropic and OpenAI on Tuesday announced new models, with both artificial intelligence AI companies noting that they are continuing to invest in improving alignment to combat risky behavior. Opus 5.5, per Anthropic, is a "major step up from Opus 5," and "achieves the best scores of any model to...

⚡ Weekly Recap: Rogue AI Agents, WeChat Worm, PaperCut Attacks, AI Espionage, and Rootkits

AI keeps showing up in the wrong places. Attackers are using it to speed up exploits, test defenses, and automate more of the job. Some models are also crossing lines on their own. That is not a great combination. The rest of the week is more familiar: old bugs still working, fresh exploit chains...

Anthropic Discloses Fourth AI Hacking Incident Involving Claude Opus 4.6

Anthropic on Wednesday disclosed a fourth incident in which its artificial intelligence AI model broke into real third-party systems, marking the latest in a growing list of cases that have raised concerns about the security risks posed by autonomous AI agents. The AI company said the incident...

Big Enough to Break Out: Tracking the Rising Capability of LLM Penetration-Testing Agents

Large language model LLM agents are increasingly applied to penetration testing, but we still know little about what they can do or how they fail. We compare two PentestGPT-based systems: a legacy human-in-the-loop system running the open-weight Kimi K2.5, and a newer autonomous system running...

redteam-skill

Redteam Skill — Multi-Agent Autonomous Penetration Testing Pi...

Claude Opus 4.6 Bypasses Gym Booking Limit, Cancels Other Users' Reservations in Tests

Aikido Security has published research that recreates the Australian gym-booking incident in a synthetic environment, finding that Claude Opus 4.6, running on the OpenClaw agent harness, exploited a client-side-only booking restriction in 9 of 10 runs. The original incident was first reported by...

Anthropic’s Opus 5 Is Better at Resisting Prompt Injection

The chart is interesting. On the IPI benchmark, Opus 5 improved over Opus 4.8, reducing the probability of an attacker succeeding within 15 attempts from 5.5% to 2.0%, and from 0.5% to 0.2% on 1 attempt. It also improved on Sonnet 5 5.9% at k=15 and Mythos 5 2.6%, making it the most robust model...

Anthropic Says Claude Mistook the Open Internet for a CTF and Breached Three Organizations

Anthropic on Thursday became the latest artificial intelligence AI company to reveal that three of its models, including Claude Opus 4.7, Mythos 5, and an unnamed research model, had breached three unnamed organizations during cybersecurity testing without its knowledge. The AI firm said the...

Claude Helped a Hacker Find a Way to Issue Tickets to Almost Every US Music Festival

A researcher found that using Anthropic’s Claude Opus 4.7, he could break into the website of Front Gate—used by every festival from Lollapalooza to Bonnaroo—and freely issue any ticket he chose...

Honeypot Protocol

Trusted monitoring, the standard defense in AI control, is vulnerable to adaptive attacks, collusion, and strategic attack selection. All of these exploit the fact that monitoring is passive: it observes model behavior but never probes whether the model would behave differently under different...

Anthropic Finds 22 Firefox Vulnerabilities Using Claude Opus 4.6 AI Model

Anthropic on Friday said it discovered 22 new security vulnerabilities in the Firefox web browser as part of a security partnership with Mozilla. Of these, 14 have been classified as high, seven have been classified as moderate, and one has been rated low in severity. The issues were addressed in...

Claude Opus 4.6 Finds 500+ High-Severity Flaws Across Major Open-Source Libraries

Artificial intelligence AI company Anthropic revealed that its latest large language model LLM, Claude Opus 4.6, has found more than 500 previously unknown high-severity security flaws in open-source libraries, including Ghostscript, OpenSC, and CGIF. Claude Opus 4.6, which was launched Thursday,...