OpenClaw 安全漏洞

OpenClaw is an intelligent artificial assistant open-sourced by OpenClaw. OpenClaw suffers from a security vulnerability that stems from local helper scripts following symbolic links when packaging skills, which can be exploited by an attacker to cause unintentional disclosure of local files...

OpenClaw 安全漏洞

OpenClaw is an intelligent artificial assistant open-sourced by OpenClaw. OpenClaw suffers from a security vulnerability that stems from process cleanup using system-wide process enumeration and pattern matching without verifying ownership, which can be exploited by an attacker to terminate...

CVE-2026-27488: Server-Side Request Forgery (SSRF)

OpenClaw is a personal AI assistant. In versions 2026.2.17 and below, Cron webhook delivery in src/gateway/server-cron.ts uses fetch directly, so webhook targets can reach private/metadata/internal endpoints without SSRF policy checks. This issue was fixed in version 2026.2.19...

CVE-2026-27487: Improper Neutralization of Special Elements used in an OS Command

OpenClaw is a personal AI assistant. In versions 2026.2.13 and below, when using macOS, the Claude CLI keychain credential refresh path constructed a shell command to write the updated JSON blob into Keychain via security add-generic-password -w .... Because OAuth tokens are user-controlled data,...

CVE-2026-27576: Uncontrolled Resource Consumption

OpenClaw is a personal AI assistant. In versions 2026.2.17 and below, the ACP bridge accepts very large prompt text blocks and can assemble oversized prompt payloads before forwarding them to chat.send. Because ACP runs over local stdio, this mainly affects local ACP clients for example IDE...

Allocation of Resources Without Limits or Throttling

Overview openclaw is a 🦞 OpenClaw — Personal AI Assistant Affected versions of this package are vulnerable to Allocation of Resources Without Limits or Throttling due to missing prompt-size checks in the ACP local stdio bridge. An attacker can cause reduced responsiveness and increased resource...

GHSA-CXPW-2G23-2VGW OpenClaw: ACP prompt-size checks missing in local stdio bridge could reduce responsiveness with very large inputs

Vulnerability The ACP bridge accepted very large prompt text blocks and could assemble oversized prompt payloads before forwarding them to chat.send. Because ACP runs over local stdio, this mainly affects local ACP clients for example IDE integrations that send unusually large inputs. Affected...

OpenClaw: ACP prompt-size checks missing in local stdio bridge could reduce responsiveness with very large inputs

Vulnerability The ACP bridge accepted very large prompt text blocks and could assemble oversized prompt payloads before forwarding them to chat.send. Because ACP runs over local stdio, this mainly affects local ACP clients for example IDE integrations that send unusually large inputs. Affected...

Server-side Request Forgery (SSRF)

Overview openclaw is a 🦞 OpenClaw — Personal AI Assistant Affected versions of this package are vulnerable to Server-side Request Forgery SSRF via the fetch function in the cron webhook delivery process. An attacker can access internal or private network resources by specifying malicious webhook...

OpenClaw hardened cron webhook delivery against SSRF

Affected Packages / Versions - openclaw npm package versions = 2026.2.17. Vulnerability Cron webhook delivery in src/gateway/server-cron.ts used fetch directly, so webhook targets could reach private/metadata/internal endpoints without SSRF policy checks. Fix Commits - 99db4d13e - 35851cdaf Thank...

GHSA-W45G-5746-X9FP OpenClaw hardened cron webhook delivery against SSRF

Affected Packages / Versions - openclaw npm package versions = 2026.2.17. Vulnerability Cron webhook delivery in src/gateway/server-cron.ts used fetch directly, so webhook targets could reach private/metadata/internal endpoints without SSRF policy checks. Fix Commits - 99db4d13e - 35851cdaf Thank...

UNIX Symbolic Link (Symlink) Following

Overview openclaw is a 🦞 OpenClaw — Personal AI Assistant Affected versions of this package are vulnerable to UNIX Symbolic Link Symlink Following via the packageskill.py script. An attacker can cause unintentional disclosure of local files from the packaging machine by including symlinks in a...

GHSA-R6H2-5GQQ-V5V6 OpenClaw: Reject symlinks in local skill packaging script

Vulnerability 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 containing symlinks to files outside the skill root, the...

OpenClaw Discord moderation authorization used untrusted sender identity in tool-driven flows

Overview Discord moderation action handling timeout, kick, ban used sender identity from request parameters in tool-driven flows, instead of trusted runtime sender context. Impact In setups where Discord moderation actions are enabled and the bot has the necessary guild permissions, a non-admin...

GHSA-WH94-P5M6-MR7J OpenClaw Discord moderation authorization used untrusted sender identity in tool-driven flows

Overview Discord moderation action handling timeout, kick, ban used sender identity from request parameters in tool-driven flows, instead of trusted runtime sender context. Impact In setups where Discord moderation actions are enabled and the bot has the necessary guild permissions, a non-admin...

User Impersonation

Overview openclaw is a 🦞 OpenClaw — Personal AI Assistant Affected versions of this package are vulnerable to User Impersonation via the moderation action handling process. An attacker can perform unauthorized moderation actions by spoofing sender identity fields in tool-driven flows. Note: This ...

Cline CLI 2.3.0 Supply Chain Attack Installed OpenClaw on Developer Systems

In yet another software supply chain attack, the open-source, artificial intelligence AI-powered coding assistant Cline CLI was updated to stealthily install OpenClaw, a self-hosted autonomous AI agent that has become exceedingly popular in the past few months. "On February 17, 2026, at 3:26 AM P...

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-2026-27007

OpenClaw is a personal AI assistant. Prior to version 2026.2.15, normalizeForHash in src/agents/sandbox/config-hash.ts recursively sorted arrays that contained only primitive values. This made order-sensitive sandbox configuration arrays hash to the same value even when order changed. In OpenClaw...