CVE-2026-82537

Roo-Code through 3.54.0 contains an auto-approve bypass vulnerability that allows attackers to execute denied shell commands by exploiting a word-boundary mismatch in comment handling between the approval gate's shell parser and bash. Attackers can craft a command string with an allowlisted word...

CVE-2026-82537

Roo-Code through version 3.54.0 contains an auto-approve bypass vulnerability caused by a word-boundary mismatch in comment handling between the approval gate's shell parser and bash . An attacker can craft a command string pairing an allowlisted word with a hash character, separator, and a denie...

EUVD-2026-74041

Roo-Code through 3.54.0 contains an auto-approve bypass vulnerability that allows attackers to execute denied shell commands by exploiting a word-boundary mismatch in comment handling between the approval gate's shell parser and bash. Attackers can craft a command string with an allowlisted word...

CVE-2026-82537 Roo-Code 3.54.0 Auto-Approve Bypass via Shell Parser Word-Boundary Mismatch

Roo-Code through 3.54.0 contains an auto-approve bypass vulnerability that allows attackers to execute denied shell commands by exploiting a word-boundary mismatch in comment handling between the approval gate's shell parser and bash. Attackers can craft a command string with an allowlisted word...

EUVD-2026-74040

Roo-Code through 3.54.0 contains an auto-approve bypass vulnerability in the shell command parsing logic that allows attackers to execute denied shell commands by exploiting the omission of the bash pipe operator from the command parser's operator token set. Attackers can craft a command line wit...

CVE-2026-82536

Roo-Code through version 3.54.0 contains an auto-approve bypass in its shell command parsing logic. The root cause is the omission of the bash pipe operator (specifically the stderr-redirecting pipe) from the parser's operator token set. An attacker can craft a command line combining an allowlist...

CVE-2026-80219

A flaw in hawtio-operator (OpenShift cluster mode) allows OAuth token theft. The operator creates a cluster-scoped OAuthClient with GrantMethod: auto and no client secret (public client). Because redirect URIs are derived from an operator-created Route whose hostname is tenant-controlled via the ...

CVE-2026-8840

The Booking calendar, Appointment Booking System plugin for WordPress is vulnerable to authorization bypass in all versions up to, and including, 3.2.36. This is due to the plugin not properly verifying that a user is authorized to perform an action. This makes it possible for unauthenticated...

CVE-2026-14322 Timetics < 1.0.57 - Unauthenticated Booking Auto-Approval via Arbitrary payment_method

The Timetics WordPress plugin before 1.0.57 does not enforce a pending or unpaid status for new bookings created through a payment method other than its recognised gateways, allowing unauthenticated users to create fully-approved bookings for priced appointments without making any payment...

CVE-2026-63108

Roo Code through 3.54.0 contains a command injection vulnerability in the auto-approve execute feature that allows attackers to bypass allowlist/denylist enforcement by nesting command substitutions inside parameter expansion defaults. The command parser in parse-command.ts replaces parameter...

CVE-2026-63108 Roo Code 3.54.0 Command Injection via Parameter Expansion Parsing

Roo Code through 3.54.0 contains a command injection vulnerability in the auto-approve execute feature that allows attackers to bypass allowlist/denylist enforcement by nesting command substitutions inside parameter expansion defaults. The command parser in parse-command.ts replaces parameter...

CVE-2026-63108 Roo Code 3.54.0 Command Injection via Parameter Expansion Parsing

Roo Code through 3.54.0 contains a command injection vulnerability in the auto-approve execute feature that allows attackers to bypass allowlist/denylist enforcement by nesting command substitutions inside parameter expansion defaults. The command parser in parse-command.ts replaces parameter...

CVE-2026-63108

Roo Code up to 3.54.0 contains a command injection via the auto-approve execute feature. The vulnerability arises because the command parser in parse-command.ts replaces parameter expansions with opaque placeholders before extracting command substitutions, causing the containsDangerousSubstitutio...

PT-2026-61774

Name of the Vulnerable Software and Affected Versions praisonai-agents affected versions not specified Description The execute code tool contains a flaw in its subprocess sandbox that allows an arbitrary read primitive over blocklisted attributes. The issue arises from the combination of two...

CVE-2026-45311

CodeWhale is a DeepSeek + MiMo coding agent in terminal. From 0.3.0 to 0.8.23, the runtests tool executes cargo test in the workspace with ApprovalRequirement::Auto, meaning it runs without any user approval prompt. cargo test compiles and executes arbitrary code: test binaries, build.rs build...

DeepSeek TUI: task_create Insecure Defaults Enable RCE via Prompt Injection in Project Files

Summary The taskcreate tool spawns durable sub-agents that inherit two insecure defaults: - allowshell defaults to true config.rs:1499: self.allowshell.unwraportrue - autoapprove defaults to true taskmanager.rs:297: autoapprove: Sometrue When a user approves a taskcreate call which requires...

GHSA-72W5-PF8H-XFP4 DeepSeek TUI: task_create Insecure Defaults Enable RCE via Prompt Injection in Project Files

Summary The taskcreate tool spawns durable sub-agents that inherit two insecure defaults: - allowshell defaults to true config.rs:1499: self.allowshell.unwraportrue - autoapprove defaults to true taskmanager.rs:297: autoapprove: Sometrue When a user approves a taskcreate call which requires...

CVE-2026-40149

PraisonAI is a multi-agent teams system. Prior to 4.5.128, the gateway's /api/approval/allow-list endpoint permits unauthenticated modification of the tool approval allowlist when no authtoken is configured the default. By adding dangerous tool names e.g., shellexec, filewrite to the allowlist, a...

Exposure of Sensitive Information Through Environmental Variables

Overview PraisonAI is a PraisonAI is an AI Agents Framework with Self Reflection. PraisonAI application combines PraisonAI Agents, AutoGen, and CrewAI into a low-code solution for building and managing multi-agent LLM systems, focusing on simplicity, customisation, and efficient human-agent...

GHSA-RCX4-77X4-HJX5 Duplicate Advisory: OpenClaw ACP client has permission auto-approval bypass via untrusted tool metadata

Duplicate Advisory This advisory has been withdrawn because it is a duplicate of GHSA-7jx5-9fjg-hp4m. This link is maintained to preserve external references. Original Description OpenClaw versions prior to 2026.2.23 contain an authorization bypass vulnerability in the ACP client that auto-approv...