CVE-2026-27001 OpenClaw: Unsanitized CWD path injection into LLM prompts
Attackers can inject malicious instructions into LLM prompts via unsanitized directory names, potentially executing arbitrary code or bypassing security controls.
- Exploited in the wild
- Not known
- Login needed
- Not needed
- Attackable
- Local or same network only
- Victim action needed
- Not needed
- Fix
- Available
What is CVE-2026-27001?
CVE-2026-27001 is a high-severity code injection vulnerability in Openclaw Openclaw, published on 19 Feb 2026. It can only be exploited from the same machine or local network, with no action from the victim.
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.
Weakness: CWE-77
Which versions are affected by CVE-2026-27001?
2 open source packages ship an affected version, including openclaw. It affects 1 product.
| Package | Affected | Fixed in |
|---|---|---|
openclaw npm | All versions | 2026.2.15 |
openclaw npm | All versions | 2026.2.15 |
Products include Openclaw Openclaw.
How do I fix CVE-2026-27001?
Upgrade openclaw to 2026.2.15 or later.
Upgrade, and never evaluate templates, expressions or code built from user input. More about Code injection.
Is CVE-2026-27001 being exploited?
There is no known exploitation of CVE-2026-27001 in the wild and no public exploit code.
Other vulnerabilities in Openclaw Openclaw
- CVE-2026-28363 Security feature bypass in OpenClaw
- CVE-2026-30741 Code injection in n/a
- CVE-2026-33579 OpenClaw < 2026.3.28 - Privilege Escalation via Missing Caller Scope Validation in Device Pair Approval
- CVE-2026-32922 OpenClaw < 2026.3.11 - Privilege Escalation via Unvalidated Scope in device.token.rotate
- CVE-2026-32978 OpenClaw < 2026.3.11 - Approval Bypass via Unrecognized Script Runners
Sources
Also known as GHSA-2qj5-gwg2-xwc4.