RCE in Openclaw
CVE-2026-27001
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.
Vulnerability class: Command Injection (OS Command Injection)
EPSS: 0.002 (10.8th percentile) — read the EPSS interpretation.
CVSS v3 metric
CVSS v3 base score 7.8 (High). Vector: CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H.
Affected products
- Openclaw — versions < 2026.2.15
Weakness classification (CWE)
References
- security-advisories@github.com (x_refsource_CONFIRM, Patch, Vendor Advisory)
- security-advisories@github.com (Patch, x_refsource_MISC)
- security-advisories@github.com (Product, x_refsource_MISC, Release Notes)
Frequently asked questions
- What is CVE-2026-27001?
- CVE-2026-27001 is a high-severity vulnerability in Openclaw, classified under Command Injection. CVSS score: 7.8/10. Published 2026-02-20.
- How severe is CVE-2026-27001?
- High severity. CVSS v3 base score is 7.8 out of 10.