OpenClaw's non-default autoAllowSkills setting could bypass on-miss exec prompt

Summary In openclaw versions up to and including 2026.2.22-2, a non-default exec-approval configuration could allow a skill-name collision to bypass an ask=on-miss prompt. When autoAllowSkills=true, a path-scoped executable such as ./skill-bin could resolve to basename skill-bin, satisfy the skil...

GHSA-77HF-7FQF-F227 OpenClaw skills-install-download: tar.bz2 extraction bypassed archive safety parity checks (local DoS)

Summary The tar.bz2 installer path in src/agents/skills-install-download.ts used shell tar preflight/extract logic that did not share the same hardening guarantees as the centralized archive extractor. This allowed crafted .tar.bz2 archives to bypass special-entry blocking and extracted-size...

Directory Traversal

Overview openclaw is a 🦞 OpenClaw — Personal AI Assistant Affected versions of this package are vulnerable to Directory Traversal via the sandbox skill mirroring command. An attacker can cause files to be written outside the intended workspace by supplying a crafted skill package with traversal...

GHSA-XW4P-PW82-HQR7 OpenClaw's sandbox skill mirroring path traversal vulnerability could write outside the sandbox workspace

Overview In affected versions, OpenClaw’s sandbox skill mirroring used the skill’s frontmatter name as part of the destination path when copying skills into the sandbox workspace. A crafted skill name containing traversal segments for example ../ or an absolute path could cause the copy to write...

OpenClaw's sandbox skill mirroring path traversal vulnerability could write outside the sandbox workspace

Overview In affected versions, OpenClaw’s sandbox skill mirroring used the skill’s frontmatter name as part of the destination path when copying skills into the sandbox workspace. A crafted skill name containing traversal segments for example ../ or an absolute path could cause the copy to write...

OpenClaw has an unspecified vulnerability (CNVD-2026-13377)

OpenClaw is an intelligent artificial assistant open-sourced by OpenClaw. OpenClaw suffers from an unspecified vulnerability that stems from insufficient validation of the targetDir value during download skill installation, which can be exploited by an attacker to cause files to be written outsid...

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...

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...

PT-2026-24944

Name of the Vulnerable Software and Affected Versions OpenClaw versions 2026.2.19-2 Description A flaw exists in the applySkillConfigenvOverrides function within the Skill Env Handler component. This issue allows for code injection when a manipulation is executed remotely. The issue arises becaus...

Formal Analysis and Supply Chain Security for Agentic AI Skills

The rapid proliferation of agentic AI skill ecosystems -- exemplified by OpenClaw 228,000 GitHub stars and Anthropic Agent Skills 75,600 stars -- has introduced a critical supply chain attack surface. The ClawHavoc campaign January-February 2026 infiltrated over 1,200 malicious skills into the...

Amazon: Low-Skill Hacker Used AI Tools to Breach FortiGate Devices Globally

Amazon says a Russian speaking low-skill hacker used AI tools to breach hundreds of FortiGate devices worldwide, showing how AI can scale cyberattacks with basic methods...

Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks

LLM agents are evolving rapidly, powered by code execution, tools, and the recently introduced agent skills feature. Skills allow users to extend LLM applications with specialized third-party code, knowledge, and instructions. Although this can extend agent capabilities to new domains, it creates...

OpenClaw < 2026.2.15 Multiple Vulnerabilities

The version of the OpenClaw AI assistant installed on the remote host is prior to 2026.2.15. It is, therefore, affected by multiple vulnerabilities, including: - A configuration injection issue in the Docker tool sandbox could allow dangerous Docker options such as bind mounts, host networking, a...

CVE-2026-27485

OpenClaw is a personal AI assistant. In versions 2026.2.17 and below, skills/skill-creator/scripts/packageskill.py a local helper script used when authors package skills previously followed symlinks while building .skill archives. If an author runs this script on a crafted local skill directory...

CVE-2026-27485

OpenClaw is a personal AI assistant. In versions 2026.2.17 and below, skills/skill-creator/scripts/packageskill.py a local helper script used when authors package skills previously followed symlinks while building .skill archives. If an author runs this script on a crafted local skill directory...

CVE-2026-27485 OpenClaw affected by Stored XSS in Control UI via unsanitized assistant name/avatar in inline script injection

OpenClaw is a personal AI assistant. In versions 2026.2.17 and below, skills/skill-creator/scripts/packageskill.py a local helper script used when authors package skills previously followed symlinks while building .skill archives. If an author runs this script on a crafted local skill directory...

CVE-2026-27485

OpenClaw is a personal AI assistant. In versions 2026.2.17 and below, skills/skill-creator/scripts/packageskill.py a local helper script used when authors package skills previously followed symlinks while building .skill archives. If an author runs this script on a crafted local skill directory...

CVE-2026-27485

Summary (concrete details): CVE-2026-27485 affects OpenClaw’s npm package, specifically the packaging helper script under skills/skill-creator/scripts/package_skill.py. The vulnerability arises when the script, run on a crafted local skill directory, follows symlinks to files outside the skill ro...