Summary
OpenClaw: Unsanitized CWD path injection into LLM prompts
Overview
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.
Affected Packages / Versions
- Package:
openclaw(npm) - Vulnerable versions:
< 2026.2.15(latest published vulnerable version as of 2026-02-16:2026.2.14) - Patched versions:
>= 2026.2.15
Fix Commit(s)
6254e96acf16e70ceccc8f9b2abecee44d606f79
Thanks @aether-ai-agent for reporting.
Impact
Prompt injection may alter agent behavior and could lead to unintended tool use or disclosure of sensitive information.
Untrusted input is inserted into a command that is later executed by the application, allowing the attacker to alter the intent of that command. Typical impact: arbitrary command execution in the application's environment.
Affected versions
Security releases
Kodem intelligence
Severity tells you how bad this could be in the worst case. It does not tell you whether you are exposed. Exploitability and impact are functions of runtime truth: whether the vulnerable code is present, reachable, and actually executes in your application. A vulnerable package can sit in your dependency tree and never run.
Kodem, an Intelligent Application Security platform, uses runtime intelligence to reveal which vulnerabilities actually execute in production, so teams prioritize the ones that genuinely matter. Kodem's runtime-powered SCA identifies whether this CVE is reachable in your applications.
Already deployed Kodem?
See it in your environmentNew to Kodem? Get a demo →Remediation advice
The workspace path is now 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.
Frequently Asked Questions
- What is CVE-2026-27001? CVE-2026-27001 is a high-severity command injection vulnerability in openclaw (npm), affecting versions < 2026.2.15. It is fixed in 2026.2.15. Untrusted input is inserted into a command that is later executed by the application, allowing the attacker to alter the intent of that command.
- Which versions of openclaw are affected by CVE-2026-27001? openclaw (npm) versions < 2026.2.15 is affected.
- Is there a fix for CVE-2026-27001? Yes. CVE-2026-27001 is fixed in 2026.2.15. Upgrade to this version or later.
- Is CVE-2026-27001 exploitable, and should I be worried? Whether CVE-2026-27001 is exploitable in your environment depends on whether the vulnerable code is present and reachable. A CVSS score is a worst-case rating; it does not account for your specific deployment, configuration, or usage patterns. Kodem, an Intelligent Application Security platform, uses runtime intelligence to show which vulnerabilities actually execute in production, so you can focus on the ones that represent real risk. Get a demo
- What actually determines whether CVE-2026-27001 is exploitable, and how bad it is? Exploitability and impact are not fixed properties of a CVE. They depend on runtime truth: whether the vulnerable code is present, reachable, and actually executes in your application. A high CVSS score on a dependency that never runs is not the same as real risk. Kodem, an Intelligent Application Security platform, uses runtime intelligence to reveal which vulnerabilities actually execute in production, so teams prioritize the ones that genuinely matter.
- How do I fix CVE-2026-27001? Upgrade
openclawto 2026.2.15 or later.