@anthropic-ai/claude-code has Sed Command Validation Bypass that Allows Arbitrary File Writes

Due to an error in sed command parsing, it was possible to bypass the Claude Code read-only validation and write to arbitrary files on the host system. Users on standard Claude Code auto-update will have received this fix automatically. Users performing manual updates are advised to update to the...

ai-sdk-provider-claude-code (>=0.2.0, <=1.0.0-beta.1), locadex (0.0.2-alpha.1) potentially affected by CVE-2025-65099 via @anthropic-ai/claude-code (>=1.0.8, <=1.0.24)

@anthropic-ai/claude-code NPM version =1.0.8, =0.2.0, =1.0.0-beta.1 - locadex 0.0.2-alpha.1 Source cves: CVE-2025-65099 Source advisory: SNYK:JS-ANTHROPICAICLAUDECODE-14073012...

ai-sdk-provider-claude-code (>=0.2.0, <=1.0.0-beta.1), locadex (0.0.2-alpha.1) potentially affected by CVE-2025-65099 via @anthropic-ai/claude-code (>=1.0.8, <=1.0.24)

@anthropic-ai/claude-code NPM version =1.0.8, =0.2.0, =1.0.0-beta.1 - locadex 0.0.2-alpha.1 Source cves: CVE-2025-65099 Source advisory: GHSA-5HHX-V7F6-X7GV...

EUVD-2025-198179

Claude Code vulnerable to command execution prior to startup trust dialog...

GHSA-5HHX-V7F6-X7GV Claude Code vulnerable to command execution prior to startup trust dialog

When using Claude Code with Yarn installed, Yarn config files can trigger code execution when running yarn --version. This could lead to a bypass of the directory trust dialog in Claude Code, as plugins and yarnPath could be executed prior to the user accepting the risks of working in an untruste...

ai-sdk-provider-claude-code (>=0.2.0, <=1.0.0-beta.1), locadex (0.0.2-alpha.1) potentially affected by CVE-2025-65099 via @anthropic-ai/claude-code (>=1.0.8, <=1.0.24)

@anthropic-ai/claude-code NPM version =1.0.8, =0.2.0, =1.0.0-beta.1 - locadex 0.0.2-alpha.1 Source cves: CVE-2025-65099 Source advisory: OSV:GHSA-5HHX-V7F6-X7GV...

Claude Code vulnerable to command execution prior to startup trust dialog

When using Claude Code with Yarn installed, Yarn config files can trigger code execution when running yarn --version. This could lead to a bypass of the directory trust dialog in Claude Code, as plugins and yarnPath could be executed prior to the user accepting the risks of working in an untruste...

Arbitrary Code Injection

Overview @anthropic-ai/claude-code is an Use Claude, Anthropic's AI assistant, right from your terminal. Claude can understand your codebase, edit files, run terminal commands, and handle entire workflows for you. Affected versions of this package are vulnerable to Arbitrary Code Injection via ya...

CVE-2025-65099

Claude Code is an agentic coding tool. Prior to version 1.0.39, when running on a machine with Yarn 3.0 or above, Claude Code could have been tricked to execute code contained in a project via yarn plugins before the user accepted the startup trust dialog. Exploiting this would have required a us...

CVE-2025-65099 Claude Code vulnerable to command execution prior to startup trust dialog

Claude Code is an agentic coding tool. Prior to version 1.0.39, when running on a machine with Yarn 3.0 or above, Claude Code could have been tricked to execute code contained in a project via yarn plugins before the user accepted the startup trust dialog. Exploiting this would have required a us...

@4via6/relay (>=1.0.0, <=1.1.3), @axonpush/wizard (>=0.0.1, <=0.0.4) +12 more potentially affected by CVE-2025-65099 via @anthropic-ai/claude-code (>=0.2.14, <=1.0.24)

@anthropic-ai/claude-code NPM version =0.2.14, =1.0.0, =0.0.1, =0.0.55, =1.0.0, =0.0.1, =0.2.0, =0.0.1, =1.8.0, =1.4.0, =0.0.1-beta.2, =0.0.1, =0.0.5 - locadex 0.0.2-alpha.1 Source cves: CVE-2025-65099 Source advisory: MEND:CVE-2025-65099...

CVE-2025-65099

Claude Code is an agentic coding tool. Prior to version 1.0.39, when running on a machine with Yarn 3.0 or above, Claude Code could have been tricked to execute code contained in a project via yarn plugins before the user accepted the startup trust dialog. Exploiting this would have required a us...

CVE-2025-65099 Claude Code vulnerable to command execution prior to startup trust dialog

Claude Code is an agentic coding tool. Prior to version 1.0.39, when running on a machine with Yarn 3.0 or above, Claude Code could have been tricked to execute code contained in a project via yarn plugins before the user accepted the startup trust dialog. Exploiting this would have required a us...

CVE-2025-65099 Claude Code vulnerable to command execution prior to startup trust dialog

Claude Code is an agentic coding tool. Prior to version 1.0.39, when running on a machine with Yarn 3.0 or above, Claude Code could have been tricked to execute code contained in a project via yarn plugins before the user accepted the startup trust dialog. Exploiting this would have required a us...

CVE-2025-65099: Improper Control of Generation of Code

Claude Code is an agentic coding tool. Prior to version 1.0.39, when running on a machine with Yarn 3.0 or above, Claude Code could have been tricked to execute code contained in a project via yarn plugins before the user accepted the startup trust dialog. Exploiting this would have required a us...

PT-2025-47513

Name of the Vulnerable Software and Affected Versions Claude Code versions prior to 1.0.39 Description Prior to version 1.0.39, Claude Code could be tricked into executing code contained in a project through Yarn plugins before the user accepted the startup trust dialog, when running on a machine...

Claude Code injection vulnerability

Claude Code is an open source proxy coding tool from Anthropic. A code injection vulnerability exists in Claude Code versions prior to 1.0.39, which stems from the possibility of executing project code via the yarn plugin without the user having to accept the startup trust dialog in Yarn 3.0 and...

Chinese Hackers Use Anthropic's AI to Launch Automated Cyber Espionage Campaign

State-sponsored threat actors from China used artificial intelligence AI technology developed by Anthropic to orchestrate automated cyber attacks as part of a "highly sophisticated espionage campaign" in mid-September 2025. "The attackers used AI's 'agentic' capabilities to an unprecedented degre...

Redefining Enterprise Defense in the Era of AI-Led Cyberattacks

More cybercriminals are turning to using autonomous AI tools to upgrade their attacks, as exemplified by the recent utilization of Anthropic’s Claude Code, prompting an urgent need for enterprises to adopt agentic AI-driven security platforms and proactive defenses to counter AI-related threats...

Malware in @chatclub/claude-code

Any computer that has this package installed or running should be considered fully compromised. All secrets and keys stored on that computer should be rotated immediately from a different computer. The package should be removed, but as full control of the computer may have been given to an outsid...