OpenClaw 安全漏洞

OpenClaw is an intelligent artificial assistant open-sourced by OpenClaw. OpenClaw has a security vulnerability that can be exploited by an attacker to execute native code after an operator approves misleading command text...

CVE-2026-30310

In its design for automatic terminal command execution, Sixth offers two options: Execute safe commands and Execute all commands. The description for the former states that commands determined by the model to be safe will be automatically executed, whereas if the model judges a command to be...

PT-2026-29257

Name of the Vulnerable Software and Affected Versions OpenClaw versions prior to 2026.3.28 Description OpenClaw contains an insufficient scope validation issue in the node pairing approval path. This allows low-privilege operators to approve nodes with broader scopes than they are authorized to,...

PT-2026-29254

DSAI-Cline's command auto-approval module contains a critical OS command injection vulnerability that renders its whitelist security mechanism completely ineffective. The system relies on string-based parsing to validate commands; while it intercepts dangerous operators such as ;, &&, ||, |, and...

PT-2026-29351

Name of the Vulnerable Software and Affected Versions Admidio versions prior to 5.0.8 Description Admidio, a user management solution, allows attackers to bypass manual registration approval and potentially take over accounts. The create user, assign member, and assign user action modes in...

CVE-2026-30311

Summary: Ridvay Code’s command auto-approval module contains a critical OS command injection vulnerability. The whitelist relies on fragile regular expressions that do not account for standard Shell command substitutions (e.g., $(...) and backticks), allowing an attacker to craft commands such as...

CVE-2026-30312

DSAI-Cline's command auto-approval module contains a critical OS command injection vulnerability that renders its whitelist security mechanism completely ineffective. The system relies on string-based parsing to validate commands; while it intercepts dangerous operators such as ;, &&, ||, |, and...

OpenClaw 安全漏洞

OpenClaw is an intelligent artificial assistant open-sourced by OpenClaw. OpenClaw suffers from an approval bypass vulnerability that stems from variable script operands in system.run not being bound between the approval and execution phases, which can be exploited by an attacker to cause an...

CVE-2026-30310

In its design for automatic terminal command execution, Sixth offers two options: Execute safe commands and Execute all commands. The description for the former states that commands determined by the model to be safe will be automatically executed, whereas if the model judges a command to be...

PT-2026-29271

Ridvay Code's command auto-approval module contains a critical OS command injection vulnerability that renders its whitelist security mechanism completely ineffective. The system relies on fragile regular expressions to parse command structures; while it attempts to intercept dangerous operations...

CVE-2026-30314

Ridvay Code's command auto-approval module contains a critical OS command injection vulnerability that renders its whitelist security mechanism completely ineffective. The system relies on fragile regular expressions to parse command structures; while it attempts to intercept dangerous operations...

PT-2026-29248

In its design for automatic terminal command execution, Sixth offers two options: Execute safe commands and Execute all commands. The description for the former states that commands determined by the model to be safe will be automatically executed, whereas if the model judges a command to be...

CVE-2026-30311

Ridvay Code's command auto-approval module contains a critical OS command injection vulnerability that renders its whitelist security mechanism completely ineffective. The system relies on fragile regular expressions to parse command structures; while it attempts to intercept dangerous operations...

CVE-2026-30312

CVE-2026-30312 affects DSAI-Cline’s command auto-approval module. AOS command injection exists due to newline characters embedded in whitelisted input, bypassing the string-based validation and causing the PowerShell interpreter to treat the newline as a separator, which can lead to Remote Code E...

CVE-2026-30314

Ridvay Code’s command auto-approval module contains a critical OS command injection vulnerability. The whitelist relies on fragile regular expressions that fail to account for Shell command substitution ($(…) and backticks), enabling an attacker to craft commands like git log --grep="$(malicious_...

EUVD-2026-17188

Roo Code's command auto-approval module contains a critical OS command injection vulnerability that renders its whitelist security mechanism completely ineffective. The system relies on fragile regular expressions to parse command structures; while it attempts to intercept dangerous operations, i...

EUVD-2026-17203

In its design for automatic terminal command execution, SakaDev offers two options: Execute safe commands and execute all commands. The description for the former states that commands determined by the model to be safe will be automatically executed, whereas if the model judges a command to be...

EUVD-2026-17186

Syntx's command auto-approval module contains a critical OS command injection vulnerability that renders its whitelist security mechanism completely ineffective. The system relies on fragile regular expressions to parse command structures; while it attempts to intercept dangerous operations, it...

EUVD-2026-17204

In its design for automatic terminal command execution, HAI Build Code Generator offers two options: Execute safe commands and Execute all commands. The description for the former states that commands determined by the model to be safe will be automatically executed, whereas if the model judges a...

CVE-2026-30308

In its design for automatic terminal command execution, HAI Build Code Generator offers two options: Execute safe commands and Execute all commands. The description for the former states that commands determined by the model to be safe will be automatically executed, whereas if the model judges a...