Tag: Anthropic
Red Team Rollout of Anthropic AI Model Hits Early Security Snag
A restricted security evaluation of Anthropic's next generation AI model was disrupted when unauthorized API access was resold through a…
Anthropic Fixes Claude Code GitHub Action Flaw Allowing Remote Repository Takeover
A permission bypass in the Claude Code GitHub Action let attackers inject malicious prompts through GitHub issues to steal repository…
Anthropic Widens Access to Claude Mythos Preview for 150 More Organizations
The expansion adds 150 organizations across critical infrastructure sectors, including power, water, healthcare, and communications, to Anthropic's defensive AI initiative.
Anthropic Security Plugin Monitors AI Code Edits for Vulnerabilities in Real Time
Anthropic's new security-guidance plugin for Claude Code reviews code edits, model outputs, and commits across three checkpoints to catch vulnerabilities…
Anthropic Prepares Commercial Release of Claude Mythos AI Model for Enterprise Security
Technical signals and internal documents suggest Anthropic is preparing to offer its previously restricted Claude Mythos AI model through Claude…
Anthropic’s Claude Mythos AI Uncovers Thousands of Critical Flaws in Key Software
Anthropic's Claude Mythos Preview AI identified over 10,000 high-severity flaws in critical software, with 97 findings already patched upstream.
AI Model Now Constructs Working Exploits from Vulnerability Chains
Anthropic's Mythos Preview AI model can now chain multiple low severity bugs into working proof-of-concept exploits, reducing the time between…
Anthropic Patches Critical Claude Code Flaw Allowing Silent Command Execution
A parsing flaw in Claude Code's deeplink handler allowed attackers to inject malicious hooks that execute commands automatically when a…