Running OpenClaw safely: identity, isolation, and runtime risk

Self-hosted agent runtimes like OpenClaw are showing up fast in enterprise pilots, and they introduce a blunt reality: OpenClaw includes limited built-in security controls. The runtime can ingest untrusted text, download and execute skills i.e. code from external sources, and perform actions usin...

MAL-2026-1380 Malicious code in cline (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 38d7531f4d4af07fee607e1d2985d0ea5b41dbf28cca5bc16c8457934e372f86 The package cline was found to contain malicious code. Source: ghsa-malware 3c16746b2d863d4c24bbc2297611c642a02942b47d12b675c4a3120911c72eec...

GHSA-9PPG-JX86-FQW7 Unauthorized npm publish of [email protected] with modified postinstall script

Description On February 17, 2026 at 3:26 AM PT, an unauthorized party used a compromised npm publish token to publish an update to Cline CLI on the NPM registry: [email protected]. The published package contains a modified package.json with an added postinstall script: "postinstall": "npm install -g...

Malicious code in cline (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 38d7531f4d4af07fee607e1d2985d0ea5b41dbf28cca5bc16c8457934e372f86 The package cline was found to contain malicious code. Source: ghsa-malware 3c16746b2d863d4c24bbc2297611c642a02942b47d12b675c4a3120911c72eec...

Infostealer Found Stealing OpenClaw AI Identity and Memory Files

Researchers at Hudson Rock have identified a live infection where an infostealer exfiltrated a victim’s OpenClaw configuration. The discovery highlights a shift in malware behaviour toward harvesting personal AI identity files...

CVE-2026-25474

OpenClaw is a personal AI assistant. In versions 2026.1.30 and below, if channels.telegram.webhookSecret is not set when in Telegram webhook mode, OpenClaw may accept webhook HTTP requests without verifying Telegram’s secret token header. In deployments where the webhook endpoint is reachable by ...

CVE-2026-24764

OpenClaw formerly Clawdbot is a personal AI assistant users run on their own devices. In versions 2026.2.2 and below, when the Slack integration is enabled, channel metadata topic/description can be incorporated into the model's system prompt. Prompt injection is a documented risk for LLM-driven...

CVE-2026-25474 OpenClaw has a Telegram webhook request forgery (missing `channels.telegram.webhookSecret`) → auth bypass

OpenClaw is a personal AI assistant. In versions 2026.1.30 and below, if channels.telegram.webhookSecret is not set when in Telegram webhook mode, OpenClaw may accept webhook HTTP requests without verifying Telegram’s secret token header. In deployments where the webhook endpoint is reachable by ...

CVE-2026-25474 OpenClaw has a Telegram webhook request forgery (missing `channels.telegram.webhookSecret`) → auth bypass

OpenClaw is a personal AI assistant. In versions 2026.1.30 and below, if channels.telegram.webhookSecret is not set when in Telegram webhook mode, OpenClaw may accept webhook HTTP requests without verifying Telegram’s secret token header. In deployments where the webhook endpoint is reachable by ...

CVE-2026-25474

OpenClaw (openclaw) contains a vulnerability in versions 2026.1.30 and earlier where, if channels.telegram.webhookSecret is not set while operating in Telegram webhook mode, it may accept webhook requests without verifying Telegram’s secret header. This can allow an attacker who can reach the web...

CVE-2026-25474 OpenClaw has a Telegram webhook request forgery (missing `channels.telegram.webhookSecret`) → auth bypass

OpenClaw is a personal AI assistant. In versions 2026.1.30 and below, if channels.telegram.webhookSecret is not set when in Telegram webhook mode, OpenClaw may accept webhook HTTP requests without verifying Telegram’s secret token header. In deployments where the webhook endpoint is reachable by ...

CVE-2026-24764 OpenClaw has Remote Code Execution via System Prompt Injection in Slack Channel Descriptions

OpenClaw formerly Clawdbot is a personal AI assistant users run on their own devices. In versions 2026.2.2 and below, when the Slack integration is enabled, channel metadata topic/description can be incorporated into the model's system prompt. Prompt injection is a documented risk for LLM-driven...

CVE-2026-24764 OpenClaw has Remote Code Execution via System Prompt Injection in Slack Channel Descriptions

OpenClaw formerly Clawdbot is a personal AI assistant users run on their own devices. In versions 2026.2.2 and below, when the Slack integration is enabled, channel metadata topic/description can be incorporated into the model's system prompt. Prompt injection is a documented risk for LLM-driven...

CVE-2026-24764 OpenClaw has Remote Code Execution via System Prompt Injection in Slack Channel Descriptions

OpenClaw formerly Clawdbot is a personal AI assistant users run on their own devices. In versions 2026.2.2 and below, when the Slack integration is enabled, channel metadata topic/description can be incorporated into the model's system prompt. Prompt injection is a documented risk for LLM-driven...

CVE-2026-24764

OpenClaw (formerly Clawdbot) is affected by a prompt-injection vulnerability (CVE-2026-24764) when Slack integration is enabled. In versions 2026.2.2 and earlier, Slack channel metadata (topic/description) could be incorporated into the model’s system prompt, increasing the surface for injection....

PT-2026-26236

Summary tools.exec.safeBins could be bypassed for filesystem access when sort output flags -o / --output or recursive grep flags were allowed through safe-bin execution paths. Affected Packages / Versions - Package: openclaw npm - Affected versions: = 2026.2.19 - Latest published version at triag...

OpenClaw 数据伪造问题漏洞

OpenClaw is an intelligent artificial assistant open-sourced by OpenClaw. OpenClaw is vulnerable to a data forgery issue. The vulnerability stems from an unverified Telegram key token header and can be exploited by an attacker to process forged updates and perform unexpected actions...

CVE-2026-24764: Improper Neutralization of Special Elements in Output Used by a Downstream Component

OpenClaw formerly Clawdbot is a personal AI assistant users run on their own devices. In versions 2026.2.2 and below, when the Slack integration is enabled, channel metadata topic/description can be incorporated into the model's system prompt. Prompt injection is a documented risk for LLM-driven...

OpenClaw 访问控制错误漏洞

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...

OpenClaw 操作系统命令注入漏洞

OpenClaw is an intelligent artificial assistant open-sourced by OpenClaw. OpenClaw suffers from an operating system command injection vulnerability that stems from the failure of maintainer/developer scripts/update-clawtributors.ts to properly filter construct command special characters, commands...