PYSEC-2026-2676 Cortex has Untrusted Project Bootstrap Code Execution via `CLAUDE_PROJECT_DIR`

Untrusted Project Bootstrap Code Execution via CLAUDEPROJECTDIR Summary The Cortex MCP server neuro-cortex-memory treats the CLAUDEPROJECTDIR environment variable — automatically set by Claude Code to the currently open project directory — as a trusted Cortex developer checkout. When the...

PYSEC-2026-2475 FastMCP has a Command Injection vulnerability - Gemini CLI

Server names containing shell metacharacters e.g., & can cause command injection on Windows when passed to fastmcp install claude-code or fastmcp install gemini-cli. These install paths use subprocess.run with a list argument, but on Windows the target CLIs often resolve to .cmd wrappers that are...

PYSEC-2026-2428 Composio Command Execution vulnerability

composio =0.5.40 is vulnerable to Command Execution in composioopenai, composioclaude, and composiojulep via the handletoolcalls function...

PYSEC-2026-2429 Composio Command Execution vulnerability

composio =0.5.40 is vulnerable to Command Execution in composioopenai, composioclaude, and composiojulep via the handletoolcalls function...

Top AI Agents Built to Catch Malicious Code Can Be Tricked Into Running It

Ask an AI coding agent to scan open-source code for security holes, and it might run the attacker's code on your own machine instead. That is the finding in a proof-of-concept published Wednesday by the AI Now Institute, an attack it calls "Friendly Fire. " It works against Anthropic's Claude Cod...

CVE-2026-54316

A flaw was found in Claude Code, an agentic coding tool. An attacker could exploit a misconfiguration in the tool's web request functionality, known as WebFetch, where the huggingface.co domain was pre-approved without proper path restrictions. By injecting untrusted content into a Claude Code...

PYSEC-2026-1268 Composio Command Execution vulnerability

composio =0.5.40 is vulnerable to Command Execution in composioopenai, composioclaude, and composiojulep via the handletoolcalls function...

Anthropic Claude Code 2.1.59 < 2.1.128 Information Disclosure (CVE-2026-46406)

The version of Anthropic Claude Code installed on the remote host is 2.1.59 prior to 2.1.128. It is, therefore, affected by an information disclosure vulnerability: - The Claude Code /copy command wrote responses to a hardcoded, predictable path /tmp/claude/response.md without UID isolation,...

Anthropic Claude Code 2.1.38 < 2.1.163 Sandbox Escape (CVE-2026-55607)

The version of Anthropic Claude Code installed on the remote host is 2.1.38 prior to 2.1.163. It is, therefore, affected by a sandbox escape vulnerability: - Claude Code's worktree handling allowed creation of worktrees named '.git' and navigation to worktrees outside the sandbox context, enablin...

GHSA-GVPP-V77H-5W8G Cortex has Untrusted Project Bootstrap Code Execution via `CLAUDE_PROJECT_DIR`

Untrusted Project Bootstrap Code Execution via CLAUDEPROJECTDIR Summary The Cortex MCP server neuro-cortex-memory treats the CLAUDEPROJECTDIR environment variable — automatically set by Claude Code to the currently open project directory — as a trusted Cortex developer checkout. When the...

Cortex has Untrusted Project Bootstrap Code Execution via `CLAUDE_PROJECT_DIR`

Untrusted Project Bootstrap Code Execution via CLAUDEPROJECTDIR Summary The Cortex MCP server neuro-cortex-memory treats the CLAUDEPROJECTDIR environment variable — automatically set by Claude Code to the currently open project directory — as a trusted Cortex developer checkout. When the...

Unsafe Dependency Resolution

Overview neuro-cortex-memory is a Scientifically-grounded memory system based on computational neuroscience research Affected versions of this package are vulnerable to Unsafe Dependency Resolution via the CLAUDEPROJECTDIR environment variable, which is treated as a trusted source directory witho...

Anthropic Restores Claude Fable 5 After U.S. Lifts Jailbreak-Linked Export Controls

Anthropic is putting Claude Fable 5 back online worldwide. On June 30, the U.S. Commerce Department lifted the export controls it had imposed on Fable and its more tightly controlled sibling Mythos 5 about two and a half weeks earlier. Fable 5 returns to users on Wednesday, July 1, across...

PT-2026-55214

Name of the Vulnerable Software and Affected Versions neuro-cortex-memory versions 3.17.0 and later Description Local arbitrary code execution is possible because the server treats the CLAUDE PROJECT DIR environment variable as a trusted source root. When the open visualization tool is invoked, t...

CVE-2026-55607

A flaw was found in Claude Code, an agentic coding tool, in its handling of worktrees. This vulnerability allowed the creation of specially named worktrees and navigation outside of the intended secure environment, leading to what is known as a 'git directory confusion attack'. By manipulating...

CVE-2026-46406

A flaw was found in Claude Code. The /copy command created responses in a predictable, world-readable temporary file without proper isolation or symlink protection. This allowed a local unprivileged user to read sensitive information from a privileged user's Claude response, potentially containin...

New BioShocking Attack Tricks AI Browsers Into Leaking User Credentials

Convince an AI browser that it is playing a game, and it can hand over your login details. That is the finding behind BioShocking , a technique from security firm LayerX that tricked six AI browsers and assistants into copying a user's credentials and sending them to an attacker. The targets...

CVE-2026-46406

Claude Code is an agentic coding tool. From 2.1.59 until 2.1.128, the Claude Code /copy command wrote responses to a hardcoded, predictable path /tmp/claude/response.md without UID isolation, randomness, or symlink protection. The file was created world-readable 0644 in a world-traversable...

CVE-2026-55607

Claude Code is an agentic coding tool. From 2.1.38 until 2.1.163, Claude Code's worktree handling allowed creation of worktrees named ".git" and navigation to worktrees outside the sandbox context, enabling git directory confusion attacks. By exploiting symlink manipulation and git fsmonitor...

CVE-2026-55607

Claude Code is an agentic coding tool. From 2.1.38 until 2.1.163, Claude Code's worktree handling allowed creation of worktrees named ".git" and navigation to worktrees outside the sandbox context, enabling git directory confusion attacks. By exploiting symlink manipulation and git fsmonitor...