OpenClaw path traversal vulnerability (CNVD-2026-13428)

OpenClaw is an intelligent artificial assistant open-sourced by OpenClaw. OpenClaw suffers from a path traversal vulnerability. The vulnerability stems from the browser download assistant accepting uncleaned output paths, which can be exploited by an attacker to traverse a directory on a system t...

OpenClaw Access Control Error Vulnerability

OpenClaw is openclaw open source an intelligent artificial assistant. OpenClaw suffers from an Access Control Error vulnerability that stems from the @openclaw/voice-call plugin Telnyx webhook handler accepting unsigned inbound webhook requests when telnyx.publicKey is not configured, which can b...

PT-2026-23541

Name of the Vulnerable Software and Affected Versions OpenClaw versions prior to 2026.2.14 Description The gateway component fails to sanitize internal approval fields in node.invoke parameters, allowing authenticated clients to bypass exec approval gating for system.run commands. Attackers with...

OpenClaw has an unspecified vulnerability (CNVD-2026-13381)

OpenClaw is openclaw open source an intelligent artificial assistant. OpenClaw has a security vulnerability that originates from the BlueBubbles iMessage channel plugin accepting webhook requests as authenticated based only on the TCP peer address as the loopback address i.e., when a missing or...

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...

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...

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...

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...

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...

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...