Skip to content
Submit incident
AII-1001-09561
ConfirmedA court, a regulator or the organization itself has stated the core facts, or the record cites a court or regulator source.

OpenClaw hardened skill download target directory validation

OpenClaw issued a security advisory for a moderate severity vulnerability (CVE-2026-27008) in versions up to 2026.2.14 where skill download installation could write files outside the intended sandbox due to insufficient validation of targetDir values.

18 February 2026 Β· OpenClaw Β· Security and cyberattacks
18 February 2026
AII-1001-09561View source β†—
Quick facts
Organization
OpenClaw (subject)
Category
Security and cyberattacks
Source
github.com
Date
18 February 2026
Drafted by
Raidu Incident Detection

What happened

A bug in OpenClaw's skill download installation allowed targetDir values from skill frontmatter to resolve outside the per-skill tools directory if not strictly validated.

In the admin-only skills.install flow, this could write files outside the intended install sandbox.

Governance controls

The vulnerability was patched in version 2026.2.15, restricting the download installer targetDir to the per-skill tools directory to prevent arbitrary file writes.

Classification

Organization
OpenClaw (subject)
Category
Security and cyberattacks
Harm status
Potential harm
Intent
Unintentional
Timing
Post-deployment
AI systems
OpenClaw

Sources and evidence

This record was researched and written by the Index, based on the following original reporting.

github.com
https://github.com/openclaw/openclaw/security/advisories/GHSA-h7f7-89mm-pqh6
Aug 2026Claude AI agent discovers gym booking system vulnerability, cancels another user's reservationWell documentedSecurity and cyberattacksThe IndependentDiaspora Digital Media (DDM News) - Nigeria Breaking News, Africa and World News and Updates -The Indian Express+3Jun 2026Five malicious skills removed from OpenClaw ClawHub marketplaceConfirmedSecurity and cyberattacksUnit42Dark ReadingJun 2026OpenClaw AI agent vulnerabilities enable malicious skill packages to steal user dataUnder investigationSecurity and cyberattacksenglish.news.cnChina NewsApr 2026AI Agent Exploited Gym Booking API Authorization Flaw and Removed Member From WaitlistReportedSecurity and cyberattacksabc.net.auaffinda.comApr 2026Open-source AI agents expose security vulnerabilities in ChinaReportedSecurity and cyberattacksδΈœζ–Ήθ΄’ε―Œη½‘China News