CVE-2026-27001
OpenClaw: Unsanitized CWD path injection into LLM prompts
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.
Attack profile
How easy it is to exploit
- Attack vector
- Local
- Complexity
- Low
- Privileges needed
- None
- User interaction
- None
What an attacker can affect
- Confidentiality
- High
- Integrity
- High
- Availability
- High
Exploit likelihood
What each source reports
CVE List Score used
OpenClaw: Unsanitized CWD path injection into LLM prompts
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.
- Record
CVE-2026-27001- CVSS 4.0
- 8.6 High
CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N - Weakness
- CWE-77
- Updated
- 2026-11-02
EUVDEUVD-2026-8415
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.
- Record
EUVD-2026-8415- CVSS 4.0
- 8.6 High
CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N - Updated
- 2026-11-02
GitHub AdvisoriesGHSA-2qj5-gwg2-xwc4
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.
Impact
Prompt injection may alter agent behavior and could lead to unintended tool use or disclosure of sensitive information.
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
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.
Fix Commit(s)
6254e96acf16e70ceccc8f9b2abecee44d606f79
Thanks @aether-ai-agent for reporting.
- Record
GHSA-2qj5-gwg2-xwc4- CVSS 4.0
- 8.6 High
CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N - Weakness
- CWE-77
- Updated
- 2026-11-02
NVD
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.
- Record
CVE-2026-27001- CVSS 4.0
- 8.6 High
CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X - CVSS 3.1
- 7.8 High
CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H - Weakness
- CWE-77
- Updated
- 2026-11-02
OSV
OpenClaw: Unsanitized CWD path injection into LLM prompts
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.
- Record
CVE-2026-27001- CVSS 4.0
- 8.6 High
CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N - Weakness
- CWE-77
- Updated
- 2026-11-11
OSVGHSA-2qj5-gwg2-xwc4
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.
Impact
Prompt injection may alter agent behavior and could lead to unintended tool use or disclosure of sensitive information.
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
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.
Fix Commit(s)
6254e96acf16e70ceccc8f9b2abecee44d606f79
Thanks @aether-ai-agent for reporting.
- Record
GHSA-2qj5-gwg2-xwc4- CVSS 4.0
- 8.6 High
CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N - Weakness
- CWE-77
- Updated
- 2026-11-02
Affected products
Affected packages
| Package | Affected | Fixed |
|---|---|---|
openclawnpm | before 2026.2.15 | 2026.2.15 |
History
| Recorded | Changed | Sources |
|---|---|---|
| facts | OSV | |
| first indexed | CVE List, EUVD, GitHub Advisories, NVD, OSV |
Dates are when Every CVE recorded each change. Upstream dates may differ.
In short
CVE-2026-27001 is a high vulnerability (CVSS 8.6) in Openclaw, published February 18, 2026. No source lists public exploit code. EPSS puts the chance of exploitation in the next 30 days at 0.23%, the 13th percentile. Fixed in openclaw 2026.2.15.
References
github.com/openclaw/openclaw/security/advisories/GHSA-2qj5-gwg2-xwc4
nvd.nist.gov/vuln/detail/CVE-2026-27001