PT-2025-33516

Name of the Vulnerable Software and Affected Versions: Claude Code versions prior to 1.0.4 Claude Code versions prior to 1.0.24 Description: Claude Code is an agentic coding tool. Prior to version 1.0.4, it’s possible to bypass the confirmation prompts to read a file and then send file contents...

Pushing Boundaries With Claude Code

Claude Code stormed onto the programming scene when Anthropic launched it in February of this year. It moved, what Andrej Karpathy has called "The Autonomy Slider" from around a three to a solid eight. What this means is that you can give Claude Code direction, it will come up with a plan to...

CVE-2025-54795

Claude Code is an agentic coding tool. In versions below 1.0.20, an error in command parsing makes it possible to bypass the Claude Code confirmation prompt to trigger execution of an untrusted command. Reliably exploiting this requires the ability to add untrusted content into a Claude Code...

CVE-2025-54794

Claude Code is an agentic coding tool. In versions below 0.2.111, a path validation flaw using prefix matching instead of canonical path comparison, makes it possible to bypass directory restrictions and access files outside the CWD. Successful exploitation depends on the presence of or ability t...

claude-agents-md (>=1.8.0, <=1.8.5), claude-yolo (>=1.4.0, <=1.7.0) potentially affected by CVE-2025-54794 +1 more via @anthropic-ai/claude-code (>=0.2.14, <=0.2.35)

@anthropic-ai/claude-code NPM version =0.2.14, =1.8.0, =1.4.0, =1.7.0 Source cves: CVE-2025-54794, CVE-2025-547954 Source advisory: SNYK:JS-ANTHROPICAICLAUDECODE-11502064...

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 Command Injection via improper...

locadex (0.0.2-alpha.1) potentially affected by CVE-2025-54795 +1 more via @anthropic-ai/claude-code (1.0.8)

@anthropic-ai/claude-code NPM version 1.0.8 is affected by a known vulnerability. The following packages have a transitive dependency on @anthropic-ai/claude-code and may be impacted: - locadex 0.0.2-alpha.1 Source cves: CVE-2025-54795, CVE-2025-547954 Source advisory:...

CVE-2025-54795

Claude Code is an agentic coding tool. In versions below 1.0.20, an error in command parsing makes it possible to bypass the Claude Code confirmation prompt to trigger execution of an untrusted command. Reliably exploiting this requires the ability to add untrusted content into a Claude Code...

CVE-2025-54794

Claude Code is an agentic coding tool. In versions below 0.2.111, a path validation flaw using prefix matching instead of canonical path comparison, makes it possible to bypass directory restrictions and access files outside the CWD. Successful exploitation depends on the presence of or ability t...

CVE-2025-54794 Claude Code Research Preview has a Path Restriction Bypass which could allow unauthorized file access

Claude Code is an agentic coding tool. In versions below 0.2.111, a path validation flaw using prefix matching instead of canonical path comparison, makes it possible to bypass directory restrictions and access files outside the CWD. Successful exploitation depends on the presence of or ability t...

CVE-2025-54794 Claude Code Research Preview has a Path Restriction Bypass which could allow unauthorized file access

Claude Code is an agentic coding tool. In versions below 0.2.111, a path validation flaw using prefix matching instead of canonical path comparison, makes it possible to bypass directory restrictions and access files outside the CWD. Successful exploitation depends on the presence of or ability t...

CVE-2025-54794

CVE-2025-54794 – Claude Code path validation bypass : Claude Code versions older than 0.2.111 expose a directory-restriction bypass due to a path validation flaw that uses prefix matching instead of canonical path comparison. Exploitation requires either a pre-existing or creatable directory shar...

CVE-2025-54795 Claude Code echo command allowed bypass of user approval prompt for command execution

Claude Code is an agentic coding tool. In versions below 1.0.20, an error in command parsing makes it possible to bypass the Claude Code confirmation prompt to trigger execution of an untrusted command. Reliably exploiting this requires the ability to add untrusted content into a Claude Code...

CVE-2025-54795 Claude Code echo command allowed bypass of user approval prompt for command execution

Claude Code is an agentic coding tool. In versions below 1.0.20, an error in command parsing makes it possible to bypass the Claude Code confirmation prompt to trigger execution of an untrusted command. Reliably exploiting this requires the ability to add untrusted content into a Claude Code...

CVE-2025-54795 Claude Code echo command allowed bypass of user approval prompt for command execution

Claude Code is an agentic coding tool. In versions below 1.0.20, an error in command parsing makes it possible to bypass the Claude Code confirmation prompt to trigger execution of an untrusted command. Reliably exploiting this requires the ability to add untrusted content into a Claude Code...

CVE-2025-54795

CVE-2025-54795 affects Claude Code. Multiple connected sources confirm a command parsing error in versions below 1.0.20 that can bypass the in-application confirmation prompt and trigger execution of untrusted commands when attack content is fed into the Claude Code context window. Impacted data/...

Claude Code 路径遍历漏洞

Claude Code is an open source proxy coding tool from Anthropic. A path traversal vulnerability exists in versions of Claude Code prior to 0.2.111, which stems from path validation using prefix matching instead of canonical path comparison, which could lead to directory restriction bypass...

Claude Code 操作系统命令注入漏洞

Claude Code is an open source proxy coding tool from Anthropic. An operating system command injection vulnerability exists in versions of Claude Code prior to 1.0.20, which stems from a command parsing error that could lead to the unacknowledged execution of untrusted commands...

Claude Code echo command allowed bypass of user approval prompt for command execution

Due to an error in command parsing, it was possible to bypass the Claude Code confirmation prompt to trigger execution of an untrusted command. Reliably exploiting this requires the ability to add untrusted content into a Claude Code context window. Users on standard Claude Code auto-update...

locadex (0.0.2-alpha.1) potentially affected by CVE-2025-54795 via @anthropic-ai/claude-code (1.0.8)

@anthropic-ai/claude-code NPM version 1.0.8 is affected by a known vulnerability. The following packages have a transitive dependency on @anthropic-ai/claude-code and may be impacted: - locadex 0.0.2-alpha.1 Source cves: CVE-2025-54795 Source advisory: OSV:GHSA-X56V-X2H6-7J34...