Cybernews

AI assistant runs hacker’s commands just from opening a project: critical vulnerability found in Claude Code

Claude Code would execute hidden code from untrusted projects before any user confirmation, Check Point reports.
SecurityWeek

Claude Code Flaws Exposed Developer Devices to Silent Hacking

Vulnerabilities in Anthropic’s Claude Code tool could have allowed attackers to silently gain control of a developer’s computer.
GovInfoSecurity

Malicious Repo Files Could Hijack Claude Code Sessions

Check Point research found three critical flaws in Anthropic's Claude Code that allow attackers to execute arbitrary commands and steal API keys through repository ...

Anthropic Claude Code's security flaws expose devices to silent hacking, triggered from remote code execution; claims report

Security experts have identified three critical vulnerabilities in Anthropic's Claude Code, potentially allowing remote code execution and API key theft. Attackers could exploit malicious ...

Security experts flag multiple issues in Claude Code, warning

An AI assistant can quickly turn into a malicious insider, so be careful with permissions.

Check Point researchers flag critical flaws in Anthropic’s Claude Code

Cybersecurity solutions company Check Point has found critical flaws in Anthropic’s Claude Code. They cautioned that ...