Browsing Tag
Anthropic
24 posts
Scanner Poses as 32 AI Bots to Find Credentials and Private Keys
A scanner impersonates 32 AI bots, including OpenAI and Claude crawlers, to search websites for exposed credentials, private keys and cloud configuration files.
Claude Code Desktop Flaw Let Malicious HTML Steal Developer Credentials
Noma Labs found a high-severity Claude Code Desktop flaw that let malicious HTML files steal local credentials and…
Anthropic Warns Small AI Models Could Power Self-Spreading AI Worms
Anthropic finds small AI models can set up inference servers across different hardware, raising concerns about future AI…
Check Point Reports LiteLLM Flaws Enabling Admin Takeover and API Key Theft
Check Point Research found two LiteLLM vulnerabilities that could let low-privilege users execute code, access sensitive files, hijack admin accounts, and steal AI provider API keys.
Cybersecurity Startup Uses Claude AI to Hack OpenAI, Earn $6,500 Bug Bounty
Hacktron AI used Anthropic's Claude to help exploit OpenAI flaws, compromise employee accounts and reach an internal code repository, earning a $6,500 bounty.
Anthropic Finds 4th Claude AI Hacking Incident Missed in Earlier Review
Anthropic reveals a 4th Claude AI hacking incident after Opus 4.6 accessed a real system, leading to a review of 481 million evaluation transcripts.
Why Hiding Chain-of-Thought Alone Doesn’t Stop Distillation Attacks
Distillation attacks have escalated into a primary security threat for AI model providers in 2026. The US government…
Fake Claude Opus 5 App Spreads New RevStealer Windows Malware
Cybersecurity firm Morphisec has uncovered a new Windows infostealer called RevStealer, which is being distributed through a fake…
Black Hat USA 2026: One GitHub Issue Could Compromise Major AI Coding Workflows
At Black Hat USA 2026, Novee found GitHub workflow flaws in Claude Code, Gemini CLI and Codex that enabled RCE, credential theft and agent control in pipelines.
Anthropic Says Claude Models Hacked 3 Organizations During Cyber Tests
Anthropic found Claude accessed systems at three real businesses after a testing error gave its AI models live internet access during cybersecurity evaluations.