Improper Input Validation

@anthropic-ai/claude-code is vulnerable to Improper Input Validation. The vulnerability is due to an error in command parsing that allows an attacker to bypass the confirmation prompt and trigger execution of untrusted commands by injecting malicious content into a Claude Code context window...

EUVD-2025-27564

Malicious code in bioql PyPI...

CVE-2025-58764

Claude Code is an agentic coding tool. Due to an error in command parsing, versions prior to 1.0.105 were vulnerable to a bypass of the Claude Code confirmation prompt to trigger execution of an untrusted command. Reliably exploiting this requires the ability to add untrusted content into a Claud...

Claude Code rg vulnerability does not protect against approval prompt bypass

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 will...

CVE-2025-58764

Claude Code is an agentic coding tool. Due to an error in command parsing, versions prior to 1.0.105 were vulnerable to a bypass of the Claude Code confirmation prompt to trigger execution of an untrusted command. Reliably exploiting this requires the ability to add untrusted content into a Claud...

CVE-2025-58764 Claude Code rg command had Command Injection that allowed bypass of user approval prompt for command execution

Claude Code is an agentic coding tool. Due to an error in command parsing, versions prior to 1.0.105 were vulnerable to a bypass of the Claude Code confirmation prompt to trigger execution of an untrusted command. Reliably exploiting this requires the ability to add untrusted content into a Claud...

Command Injection

@anthropic-ai/claude-code is vulnerable to Command Injection. The vulnerability is due to the confirmation prompt being bypassed, allowing execution of untrusted commands if malicious content is injected into the context window...

Path Traversal

@anthropic-ai/claude-code is vulnerable to Path Traversal. The vulnerability is due to using prefix matching instead of canonical path comparison, which allows bypassing directory restrictions and accessing files outside the CWD if a directory with the same prefix exists and untrusted content is...

CVE-2025-55284

Claude Code is an agentic coding tool. Prior to version 1.0.4, it's possible to bypass the Claude Code confirmation prompts to read a file and then send file contents over the network without user confirmation due to an overly broad allowlist of safe commands. Reliably exploiting this requires th...

CVE-2025-55284

Claude Code is an agentic coding tool. Prior to version 1.0.4, it's possible to bypass the Claude Code confirmation prompts to read a file and then send file contents over the network without user confirmation due to an overly broad allowlist of safe commands. Reliably exploiting this requires th...

CVE-2025-55284 Claude Code's Permissive Default Allowlist Enables Unauthorized File Read and Network Exfiltration in Claude Code

Claude Code is an agentic coding tool. Prior to version 1.0.4, it's possible to bypass the Claude Code confirmation prompts to read a file and then send file contents over the network without user confirmation due to an overly broad allowlist of safe commands. Reliably exploiting this requires th...

CVE-2025-55284 Claude Code's Permissive Default Allowlist Enables Unauthorized File Read and Network Exfiltration in Claude Code

Claude Code is an agentic coding tool. Prior to version 1.0.4, it's possible to bypass the Claude Code confirmation prompts to read a file and then send file contents over the network without user confirmation due to an overly broad allowlist of safe commands. Reliably exploiting this requires th...

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...

RedTeamLLM: an Agentic AI Framework for Offensive Security

From automated intrusion testing to discovery of zero-day attacks before software launch, agentic AI calls for great promises in security engineering. This strong capability is bound with a similar threat: the security and research community must build up its models before the approach is leverag...