Anthropic Tests Show AI Agents Crossing Boundaries to Exploit Live Web Systems
Anthropic says internal evaluations found Claude models exploiting injection flaws, using exposed tokens and bypassing web-tool restrictions on real systems. The company has suspended live internet access for...
AI-Driven Zammad Attack Chained Two Zero-Days to Reach Root in Seconds
An AI-assisted intruder compromised the Dutch Institute for Vulnerability Disclosure by chaining two previously unknown Zammad flaws. The incident moved from session hijacking to root access in seconds...
CARBONATO Botnet Embeds an AI Agent in Compromised Docker Hosts
The CARBONATO botnet abuses unauthenticated Docker services, escapes privileged containers and installs an AI agent controlled through Telegram. Separate automated scripts spread across nearby networks while the agent...
When AI Agents Go Off-Script: OpenAI Systems Quietly Probed Four Public Websites
Newly disclosed incidents show OpenAI's autonomous agents escalating to SQL injection, path traversal, and access-control bypass attempts against government and university systems on their own, without ever being...
Low-Cost AI Agent Campaign Steals 600,000 Payment Cards From Retailers
Researchers reconstructed a campaign in which open-source AI agents autonomously scanned and exploited online retailers for an average reported cost of $25.46 per completed scan. The operation allegedly...
BragJack Lets Malicious Extensions Command AI Browser Agents Across Trusted Channels
Researchers showed that a malicious browser extension can hijack privileged communication paths used by AI assistants in five Chromium-based environments. The BragJack technique can force agent actions without...
Google Uncovers Attack Where AI Agents Ran an Entire Credential-Theft Operation With Almost No Human Help
Google Cloud researchers say they've observed attackers hand an autonomous AI agent framework a set of instructions and let it scan, exploit, and harvest more than 23,800 credentials...
AI-Orchestrated Intrusions Hit Asian Government and Political Networks
Attackers used an AI-orchestration framework alongside conventional exploits, stolen credentials and custom malware in a campaign spanning Asian government, political and education targets. The case shows how agentic...