PT-2026-23539

Name of the Vulnerable Software and Affected Versions OpenClaw versions prior to 2026.2.12 Description The software uses non-constant-time string comparison for hook token validation. This allows attackers to potentially infer tokens through timing measurements. Remote attackers with network acce...

OpenClaw code issue vulnerability (CNVD-2026-13388)

OpenClaw is openclaw open source an intelligent artificial assistant. OpenClaw suffers from a code issue vulnerability that stems from a Cron webhook delivery using fetch direct call, which can be exploited by an attacker to cause the webhook target to access private or internal endpoints...

OpenClaw Cross-Site Scripting Vulnerability

OpenClaw is an intelligent artificial assistant open-sourced by OpenClaw. A cross-site scripting vulnerability exists in OpenClaw. The vulnerability stems from improper escaping of assistant identity information when rendered by Control UI and can be exploited by an attacker to compromise...

OpenClaw Resource Management Error Vulnerability (CNVD-2026-13374)

OpenClaw is an intelligent artificial assistant open-sourced by OpenClaw. OpenClaw suffers from a Resource Management Error vulnerability that stems from an ACP bridge accepting too large a block of prompt text, which can be exploited by an attacker to cause problems with the processing of abnorm...

ClawJacked Flaw Lets Malicious Sites Hijack Local OpenClaw AI Agents via WebSocket

OpenClaw has fixed a high-severity security issue that, if successfully exploited, could have allowed a malicious website to connect to a locally running artificial intelligence AI agent and take over control. "Our vulnerability lives in the core system itself – no plugins, no marketplace, no...

CVE-2026-28363

In OpenClaw before 2026.2.23, tools.exec.safeBins validation for sort could be bypassed via GNU long-option abbreviations such as --compress-prog in allowlist mode, leading to approval-free execution paths that were intended to require approval. Only an exact string such as --compress-program was...

Clawdrain: Exploiting Tool-Calling Chains for Stealthy Token Exhaustion in OpenClaw Agents

Modern generative agents such as OpenClaw - an open-source, self-hosted personal assistant with a community skill ecosystem, are gaining attention and are used pervasively. However, the openness and rapid growth of these ecosystems often outpace systematic security evaluation. In this paper, we...

Incorrect Authorization

Overview openclaw is a 🦞 OpenClaw — Personal AI Assistant Affected versions of this package are vulnerable to Incorrect Authorization via the resolvePermissionRequest, resolveToolNameForPermission, and shouldAutoApproveToolCall functions. An attacker can gain unauthorized access to resources by...

OpenClaw ACP client has permission auto-approval bypass via untrusted tool metadata

Vulnerability Summary The OpenClaw ACP client could auto-approve tool calls based on untrusted metadata and permissive name heuristics. A malicious or compromised ACP tool invocation could bypass expected interactive approval prompts for read-class operations. Affected Packages / Versions -...

GHSA-7JX5-9FJG-HP4M OpenClaw ACP client has permission auto-approval bypass via untrusted tool metadata

Vulnerability Summary The OpenClaw ACP client could auto-approve tool calls based on untrusted metadata and permissive name heuristics. A malicious or compromised ACP tool invocation could bypass expected interactive approval prompts for read-class operations. Affected Packages / Versions -...

Multiple Releases of Same Resource or Handle

Overview openclaw is a 🦞 OpenClaw — Personal AI Assistant Affected versions of this package are vulnerable to Multiple Releases of Same Resource or Handle via the applySkillConfigEnvOverrides function. An attacker can inject dangerous environment variables into the host process by modifying local...

OpenClaw: Skill env override host env injection via applySkillConfigEnvOverrides (defense-in-depth)

Summary applySkillConfigEnvOverrides previously copied skills.entries..env values into the host process.env without applying the host env safety policy. Impact In affected versions, dangerous process-level variables such as NODEOPTIONS could be injected when unset, which can influence...

GHSA-82G8-464F-2MV7 OpenClaw: Skill env override host env injection via applySkillConfigEnvOverrides (defense-in-depth)

Summary applySkillConfigEnvOverrides previously copied skills.entries..env values into the host process.env without applying the host env safety policy. Impact In affected versions, dangerous process-level variables such as NODEOPTIONS could be injected when unset, which can influence...

ClawJacked Vulnerability in OpenClaw Could Let Websites Hijack AI Agents

Is your AI assistant safe? Oasis Security researchers have found a critical ClawJacked vulnerability in OpenClaw that allows hackers to hijack AI agents through a simple browser tab...

GHSA-7977-C43C-XPWJ OpenClaw is vulnerable to validation bypass through GNU long-option abbreviations in allowlist mode

In OpenClaw before 2026.2.23, tools.exec.safeBins validation for sort could be bypassed via GNU long-option abbreviations such as --compress-prog in allowlist mode, leading to approval-free execution paths that were intended to require approval. Only an exact string such as --compress-program was...

OpenClaw is vulnerable to validation bypass through GNU long-option abbreviations in allowlist mode

In OpenClaw before 2026.2.23, tools.exec.safeBins validation for sort could be bypassed via GNU long-option abbreviations such as --compress-prog in allowlist mode, leading to approval-free execution paths that were intended to require approval. Only an exact string such as --compress-program was...

Incomplete List of Disallowed Inputs

Overview openclaw is a 🦞 OpenClaw — Personal AI Assistant Affected versions of this package are vulnerable to Incomplete List of Disallowed Inputs in the tools.exec.safeBins validation when validating options for sort. An attacker can execute unauthorized commands by supplying GNU long-option...

CVE-2026-28363

In OpenClaw before 2026.2.23, tools.exec.safeBins validation for sort could be bypassed via GNU long-option abbreviations such as --compress-prog in allowlist mode, leading to approval-free execution paths that were intended to require approval. Only an exact string such as --compress-program was...

CVE-2026-28363

In OpenClaw before 2026.2.23, tools.exec.safeBins validation for sort could be bypassed via GNU long-option abbreviations such as --compress-prog in allowlist mode, leading to approval-free execution paths that were intended to require approval. Only an exact string such as --compress-program was...

CVE-2026-28363

In OpenClaw before 2026.2.23, tools.exec.safeBins validation for sort could be bypassed via GNU long-option abbreviations such as --compress-prog in allowlist mode, leading to approval-free execution paths that were intended to require approval. Only an exact string such as --compress-program was...