Skip to content
Submit incident
Organization/organizations/openclaw

OpenClaw

62
Records
2026
Years covered
6
Categories

Incident records62

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 cyberattacks东方财富网China NewsApr 2026China warns of risks in using OpenClaw AI agent for patent applicationsConfirmedIntellectual property and appropriation驱动之家21jingji.combjnews.com.cn+4Apr 2026OpenClaw and NemoClaw AI agents exposed to critical vulnerabilitiesConfirmedSecurity and cyberattacksnews.cnithome.com.twMar 2026Ant Group AI lab finds 8 vulnerabilities in OpenClaw autonomous agent frameworkConfirmedSecurity and cyberattacksm.163.comguancha.cnET NetMar 2026AI Agents Cause Unauthorized Actions and Security Risks in EnterprisesReportedSafety and wellbeingUDNCentral News AgencyMar 2026OpenClaw and Langflow critical vulnerabilities enable authentication bypassConfirmedSecurity and cyberattacks驱动之家net.zhiding.cnET Net+1Mar 2026OpenClaw AI agents cause data breaches and mass layoffs in ChinaWell documentedGovernance, accountability and labourvnexpress.netcafef.vnBáo Nhân Dân điện tử+5Mar 2026OpenClaw AI agent raises security and privacy concerns in ChinaUnder investigationSecurity and cyberattacksBloomberg BusinessExciteGIGAZINEMar 2026China restricts OpenClaw AI agent deployment in government and state enterprisesConfirmedSecurity and cyberattacksbbc.comTradingViewO Globo+6Feb 2026OpenClaw WebSocket vulnerability allows malicious websites to hijack local AI agentsConfirmedSecurity and cyberattacksIT Security News - cybersecurity, infosecurity newsCyberwarzoneFeb 2026OpenClaw AI Agent Deletes Meta AI Director's Emails Without AuthorizationReportedSafety and wellbeingIndia Todayhindustantimes.comFeb 2026OpenClaw symlink following vulnerability in skill packaging scriptConfirmedSecurity and cyberattacksgithub.comFeb 2026OpenClaw cron webhook delivery vulnerability CVE-2026-27488ConfirmedSecurity and cyberattacksgithub.comFeb 2026OpenClaw ACP missing prompt-size checks in stdio bridgeConfirmedSecurity and cyberattacksgithub.comFeb 2026OpenClaw unauthenticated discovery TXT records could steer routing and TLS pinningConfirmedSecurity and cyberattacksgithub.comcve.orgFeb 2026Docker container escape via unvalidated bind mount injection in OpenClawConfirmedSecurity and cyberattacksgithub.comFeb 2026OpenClaw: Telegram bot token exposure via logs (CVE-2026-27003)ConfirmedSecurity and cyberattacksgithub.comFeb 2026OpenClaw session tool visibility and Telegram webhook secret disclosureConfirmedSecurity and cyberattacksgithub.comFeb 2026OpenClaw sandbox config hash treated order-only changes as unchangedConfirmedSecurity and cyberattacksgithub.comFeb 2026OpenClaw hardened skill download target directory validationConfirmedSecurity and cyberattacksgithub.comFeb 2026Stored XSS in OpenClaw Control UI via unsanitized assistant identityConfirmedSecurity and cyberattacksgithub.comFeb 2026OpenClaw Discord moderation authorization used untrusted sender identityConfirmedSecurity and cyberattacksgithub.comFeb 2026OpenClaw Path Traversal in Browser Download FunctionalityConfirmedSecurity and cyberattacksgithub.comFeb 2026OpenClaw CLI unvalidated process kill via SIGKILL in cleanupConfirmedSecurity and cyberattacksgithub.comFeb 2026Infostealer malware steals OpenClaw AI assistant configuration filesReportedSecurity and cyberattacksTechNaduTechRadarFeb 2026OpenClaw CSRF vulnerability in loopback browser mutation endpointsConfirmedSecurity and cyberattacksgithub.comFeb 2026OpenClaw Telnyx provider accepts unauthenticated webhook requests (CVE-2026-26319)ConfirmedSecurity and cyberattacksgithub.comFeb 2026OpenClaw macOS deep link confirmation truncation can conceal executed agent messageConfirmedSecurity and cyberattacksgithub.comFeb 2026OpenClaw Feishu extension allows local file disclosure via sendMediaFeishuConfirmedSecurity and cyberattacksgithub.comFeb 2026OpenClaw Gateway tool allowed unrestricted gatewayUrl overrideConfirmedSecurity and cyberattacksgithub.comFeb 2026Command injection in OpenClaw maintainer clawtributors updaterConfirmedSecurity and cyberattacksgithub.comFeb 2026OpenClaw SSRF guard bypass via IPv4-mapped IPv6 literalsConfirmedSecurity and cyberattacksgithub.comcve.orgFeb 2026OpenClaw node host system.run rawCommand/command mismatch allows allowlist bypassConfirmedSecurity and cyberattacksgithub.comFeb 2026OpenClaw skills.status could leak secrets to operator.read clientsConfirmedSecurity and cyberattacksgithub.comFeb 2026OpenClaw iMessage group allowlist authorization inherited DM pairing-store identitiesConfirmedSecurity and cyberattacksgithub.comFeb 2026Path traversal in OpenClaw browser upload allows local file readConfirmedSecurity and cyberattacksgithub.comFeb 2026OpenClaw unsanitized current working directory path injection into LLM promptsConfirmedSecurity and cyberattacksgithub.comFeb 2026OpenClaw Slack integration vulnerable to system prompt injection via channel metadataConfirmedSecurity and cyberattacksgithub.comcve.orgFeb 2026OpenClaw Telegram webhook secret validation bypass (CVE-2026-25474)ConfirmedSecurity and cyberattacksgithub.comFeb 2026OpenClaw BlueBubbles webhook auth bypass via loopback proxy trustConfirmedSecurity and cyberattacksgithub.comFeb 2026Shell injection vulnerability in OpenClaw macOS keychain credential writeConfirmedSecurity and cyberattacksgithub.comFeb 2026OpenClaw AI agents create unauthorized dating profiles without user consentReportedPrivacy and surveillanceFortunemintFeb 2026AI Agent Publishes Attack Article After Code RejectionWell documentedHarmful and abusive contentArs TechnicaDecryptFast Company+3Feb 2026AI coding agent allegedly published accusatory blog post targeting Matplotlib maintainerAllegedHarmful and abusive contenttheregister.comFeb 2026Tens of thousands of OpenClaw AI agents exposed to public internet through misconfigurationConfirmedSecurity and cyberattacksThe Korea TimesInfosecurity MagazineFeb 2026Malicious AI skills poisoned OpenClaw plugin hubReportedSecurity and cyberattacksCointelegraphFinanceFeeds
50 of 62 shownFilter all 62 in Explore →