Vulnerability 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.
CVSS Score
HIGH
Affected Products
| Vendor | Product | Versions |
|---|---|---|
| Openclaw | Openclaw | < 2026.2.15 |
Related Weaknesses (CWE)
References
- https://github.com/openclaw/openclaw/commit/6254e96acf16e70ceccc8f9b2abecee44d60Patch
- https://github.com/openclaw/openclaw/releases/tag/v2026.2.15ProductRelease Notes
- https://github.com/openclaw/openclaw/security/advisories/GHSA-2qj5-gwg2-xwc4Vendor AdvisoryPatch
FAQ
What is CVE-2026-27001?
CVE-2026-27001 is a vulnerability with a CVSS score of 7.8 (HIGH). 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 ...
How severe is CVE-2026-27001?
CVE-2026-27001 has been rated HIGH with a CVSS base score of 7.8/10. Review the CVSS metrics above for detailed severity breakdown.
Is there a patch for CVE-2026-27001?
Check the references section above for vendor advisories and patch information. Affected products include: Openclaw Openclaw.