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.
Metrics
Affected Vendors & Products
Advisories
| Source | ID | Title |
|---|---|---|
Github GHSA |
GHSA-2qj5-gwg2-xwc4 | OpenClaw: Unsanitized CWD path injection into LLM prompts |
Fixes
Solution
No solution given by the vendor.
Workaround
No workaround given by the vendor.
References
History
Fri, 20 Feb 2026 10:15:00 +0000
| Type | Values Removed | Values Added |
|---|---|---|
| First Time appeared |
Openclaw
Openclaw openclaw |
|
| Vendors & Products |
Openclaw
Openclaw openclaw |
Thu, 19 Feb 2026 23:30:00 +0000
| Type | Values Removed | Values Added |
|---|---|---|
| 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. | |
| Title | OpenClaw: Unsanitized CWD path injection into LLM prompts | |
| Weaknesses | CWE-77 | |
| References |
| |
| Metrics |
cvssV4_0
|
Projects
Sign in to view the affected projects.
Status: PUBLISHED
Assigner: GitHub_M
Published:
Updated: 2026-02-19T23:10:07.761Z
Reserved: 2026-02-17T01:41:24.607Z
Link: CVE-2026-27001
No data.
Status : Received
Published: 2026-02-20T00:16:16.653
Modified: 2026-02-20T00:16:16.653
Link: CVE-2026-27001
No data.
OpenCVE Enrichment
Updated: 2026-02-20T09:53:27Z
Weaknesses
Github GHSA