Vulnerability · Published Feb 19, 2026 · Assigned by GitHub_M
CVE-2026-27001OpenClaw: Unsanitized CWD path injection into LLM prompts
High 8.6
In plain English
A high-severity command injection in openclaw from openclaw. There are no confirmed reports of exploitation so far. The chance it is exploited in the next 30 days is estimated at 0.2% (higher than 13% of all known vulnerabilities). Fixed versions are available - upgrade the affected package.
Official description
OpenClaw is a personal AI assistant. Prior to version 2026.2.15, OpenClaw embedded the current working directory (workspace path) into the agent system prompt without sanitization. If an attacker can cause OpenClaw to run inside a directory whose name contains control/format characters (for example newlines or Unicode bidi/zero-width markers), those characters could break the prompt structure and inject attacker-controlled instructions. Starting in version 2026.2.15, the workspace path is sanitized before it is embedded into any LLM prompt output, stripping Unicode control/format characters and explicit line/paragraph separators. Workspace path resolution also applies the same sanitization as defense-in-depth.
Affected packages & fixed versions
| Ecosystem | Package | Fixed in | Advisory |
|---|---|---|---|
| npm | openclaw | 2026.2.15 | GHSA-2qj5-gwg2-xwc4 |
Affected products (as reported)
Weakness: CWE-77 · Vector: CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N