Jailbreaking Frontier Foundation Models through Intention Deception

Large vision-language models exhibit remarkable capability but remain highly susceptible to jailbreaking. Existing safety training approaches aim to have the model learn a refusal boundary between safe and unsafe, based on the user's intent. It has been found that this binary training regime ofte...

@netlify/agent-runner-cli (>=1.83.1, <=1.94.0), feishu-claude-bot (0.1.0) +1 more potentially affected by CVE-2026-40068 via @anthropic-ai/claude-code (>=2.1.63, <=2.1.81)

@anthropic-ai/claude-code NPM version =2.1.63, =1.83.1, =1.2.2, =1.2.3 Source cves: CVE-2026-40068 Source advisory: OSV:GHSA-Q5HJ-MXQH-VV77...

Arbitrary Command 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 Command Injection via...

@netlify/agent-runner-cli (>=1.83.1, <=1.94.0), feishu-claude-bot (0.1.0) +1 more potentially affected by CVE-2026-40068 via @anthropic-ai/claude-code (>=2.1.63, <=2.1.81)

@anthropic-ai/claude-code NPM version =2.1.63, =1.83.1, =1.2.2, =1.2.3 Source cves: CVE-2026-40068 Source advisory: SNYK:JS-ANTHROPICAICLAUDECODE-16301567...

GHSA-Q5HJ-MXQH-VV77 Claude Code: Trust Dialog Bypass via Git Worktree Spoofing Allows Arbitrary Code Execution

Claude Code used the git worktree commondir file when determining folder trust but did not validate its contents. By crafting a repository with a commondir file pointing to a path the victim had previously trusted, an attacker could bypass the trust dialog and immediately execute malicious hooks...

coordinated-disclosure

coordinated-disclosure A Claude Code skill + plugin marketpla...

PT-2026-37099

Name of the Vulnerable Software and Affected Versions Claude Code versions 2.1.63 through 2.1.83 Description The folder trust determination logic fails to validate the contents of the git worktree commondir file. An attacker can craft a malicious repository with a commondir file pointing to a pat...

Anthropic Claude Code < 2.1.64 Sandbox Escape via Symlink Following (CVE-2026-39861)

The version of Anthropic Claude Code installed on the remote host is prior to 2.1.64. It is, therefore, affected by a sandbox escape vulnerability. - Claude Code's sandbox did not prevent sandboxed processes from creating symlinks pointing to locations outside the workspace. When Claude Code...

Discord-Linked Group Accessed Anthropic’s Claude Mythos AI in Vendor Breach

Anthropic is investigating a vendor breach after a Discord-linked group accessed its Claude Mythos AI model, with no evidence of impact on core systems...

AI-powered defense for an AI-accelerated threat landscape

We are at an inflection point in cybersecurity. Recent advances in AI model capabilities are changing how vulnerabilities are discovered and exploited. AI models can autonomously discover weaknesses, chain multiple lower-severity issues into working end-to-end exploits, and produce working...

Researcher claims Claude Desktop installs “spyware” on macOS

Security researcher Alexander Hanff wrote an article titled Anthropic secretly installs spyware when you install Claude Desktop. Claims like that are bound to create two sides, so we searched for an official rebuttal by Anthropic. But we couldn’t find one. It would surprise me very much if they’d...

UNIX Symbolic Link (Symlink) Following

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 UNIX Symbolic Link Symlink...

EUVD-2026-24033

Claude Code: Sandbox Escape via Symlink Following Allows Arbitrary File Write Outside Workspace...

@acampkin/mcc (>=2.1.0, <=2.5.0), @kimuson/claude-code-viewer (>=0.4.2-beta.2, <=0.6.0) +24 more potentially affected by CVE-2026-39861 via @anthropic-ai/claude-code (>=2.0.0, <=2.1.63)

@anthropic-ai/claude-code NPM version =2.0.0, =2.1.0, =0.4.2-beta.2, =19.24.1, =1.0.0-broken, =0.0.1-rc.1, =0.0.1, =0.4.0, =1.0.29, =0.12.0, =0.5.2, =0.12.1, =0.0.0, =0.1.2, =2.0.0 - ch-go 1.0.3 and more Source cves: CVE-2026-39861 Source advisory: OSV:GHSA-VP62-R36R-9XQP...

@acampkin/mcc (>=2.1.0, <=2.5.0), @kimuson/claude-code-viewer (>=0.4.2-beta.2, <=0.6.0) +24 more potentially affected by CVE-2026-39861 via @anthropic-ai/claude-code (>=2.0.0, <=2.1.63)

@anthropic-ai/claude-code NPM version =2.0.0, =2.1.0, =0.4.2-beta.2, =19.24.1, =1.0.0-broken, =0.0.1-rc.1, =0.0.1, =0.4.0, =1.0.29, =0.12.0, =0.5.2, =0.12.1, =0.0.0, =0.1.2, =2.0.0 - ch-go 1.0.3 and more Source cves: CVE-2026-39861 Source advisory: SNYK:JS-ANTHROPICAICLAUDECODE-16191021...

CVE-2026-39861

Claude Code is an agentic coding tool. Prior to version 2.1.64, Claude Code's sandbox did not prevent sandboxed processes from creating symlinks pointing to locations outside the workspace. When Claude Code subsequently wrote to a path within such a symlink, its unsandboxed process followed the...

CVE-2026-39861

Claude Code is an agentic coding tool. Prior to version 2.1.64, Claude Code's sandbox did not prevent sandboxed processes from creating symlinks pointing to locations outside the workspace. When Claude Code subsequently wrote to a path within such a symlink, its unsandboxed process followed the...

CVE-2026-39861

CVE-2026-39861 affects Claude Code prior to version 2.1.64. The sandbox could be escaped by following symlinks outside the workspace when a path under a symlink was written to, allowing an unsandboxed process to reach arbitrary locations. This could enable code execution outside the sandbox under...

CVE-2026-39861 Claude Code: Sandbox Escape via Symlink Following Allows Arbitrary File Write Outside Workspace

Claude Code is an agentic coding tool. Prior to version 2.1.64, Claude Code's sandbox did not prevent sandboxed processes from creating symlinks pointing to locations outside the workspace. When Claude Code subsequently wrote to a path within such a symlink, its unsandboxed process followed the...

CVE-2026-39861 Claude Code: Sandbox Escape via Symlink Following Allows Arbitrary File Write Outside Workspace

Claude Code is an agentic coding tool. Prior to version 2.1.64, Claude Code's sandbox did not prevent sandboxed processes from creating symlinks pointing to locations outside the workspace. When Claude Code subsequently wrote to a path within such a symlink, its unsandboxed process followed the...