Raw vector
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:XSummary
CVE-2026-27001 is a high-severity Command Injection (CWE-77) vulnerability in Openclaw Openclaw. Its CVSS base score is 8.6 (High).
Operationally, exploitation aligns with the MITRE ATT&CK technique Command and Scripting Interpreter (T1059); ranked at the 11th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog.
This vulnerability is AI-related — categorised as Enterprise AI Assistants; in the LLM/Generative AI Risks risk domain.
The strongest mitigations our analysis identified map to SA-11 (Developer Testing and Evaluation) and SI-10 (Information Input Validation) — see the control section below for these in your framework.
Deeper analysis AI-assisted summary
Synthesised by an AI model from the NVD description and linked references — a reading aid, not an authoritative source.
CVE-2026-27001 is a vulnerability in OpenClaw, a personal AI assistant, affecting versions prior to 2026.2.15. The issue arises from embedding the current working directory, or workspace path, into the agent system prompt without sanitization. Directory names containing control or format characters, such as newlines or Unicode bidi/zero-width markers, can disrupt the prompt structure and enable injection of attacker-controlled instructions. It is associated with CWE-77 and carries a CVSS v3.1 base score of 7.8 (AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H).
A local attacker with low privileges can exploit this vulnerability by running OpenClaw within a directory whose name includes malicious control or format characters. This allows the characters to break the intended prompt format, injecting arbitrary instructions into the LLM processing. Successful exploitation can result in high impacts to confidentiality, integrity, and availability.
Mitigation is addressed in the OpenClaw GitHub security advisory (GHSA-2qj5-gwg2-xwc4), commit 6254e96acf16e70ceccc8f9b2abecee44d606f79, and release v2026.2.15. Starting with version 2026.2.15, the workspace path is sanitized prior to embedding in any LLM prompt output by stripping Unicode control/format characters and explicit line/paragraph separators. Workspace path resolution also incorporates the same sanitization as a defense-in-depth measure; users are advised to upgrade immediately.
OWASP Top 10 for Web (2025)
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2026-8415
Vulnerability Data
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…
more
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.
- CWE(s)
AI Security AnalysisAI
- AI Category
- Enterprise AI Assistants
- Risk Domain
- LLM/Generative AI Risks
- OWASP Top 10 for LLMs 2025
- None mapped
- AI-specific weaknesses CR
- CWE-1427 — Unsanitized workspace path embedded in LLM system prompt enables injection via control chars.
Mapped by Cyber Resilience · not in NVD. Poisoning and extraction cases are routed to MITRE ATLAS instead of a synthetic CWE.- Classification Reason
- Matched keywords: ai, llm
Related Threats
MITRE ATT&CK Enterprise Techniques
CVEs Like This One
Affected Assets
Mitigating Controls
Control response
—
—
—
V1.2.3V1.2.5V1.2.8V1.2.9
Mitigating Controls (NIST 800-53 r5) AI
Developer testing and evaluation can discover command-construction flaws before deployment.
Input validation directly stops construction of commands from untrusted data containing special elements.
Secure engineering principles include proper neutralization and safe command construction practices.
Mitigating Controls (NIST CSF 2.0) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→CSF cross-walk (authority under review) — links open the control.
Secure SDLC practices directly require input validation and neutralization that prevent command injection.
Runtime monitoring of software and data can detect anomalous command execution resulting from injection.
Identifying recorded vulnerabilities enables remediation of command-injection flaws before exploitation.
Mitigating Controls (ISO/IEC 27001:2022 Annex A) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→ISO cross-walk (authority under review) — links open the control.
Secure coding standards require proper escaping and parameterization of commands, directly eliminating CWE-77.
Security testing in development catches command-injection vulnerabilities before release.
Secure development life cycle mandates input validation and command construction practices that directly prevent command injection.
Application security requirements explicitly call for controls against injection flaws including command injection.
Secure architecture principles reduce the attack surface but do not prescribe the specific neutralization techniques needed.
Environment separation limits the blast radius of an exploited command injection but does not prevent the flaw itself.