CVE-2026-30741
Remote Code Execution via Prompt Injection in OpenClaw Agent
Publication date: 2026-03-11
Last updated on: 2026-03-17
Assigner: MITRE
Description
Description
CVSS Scores
EPSS Scores
| Probability: | |
| Percentile: |
Meta Information
Affected Vendors & Products
| Vendor | Product | Version / Range |
|---|---|---|
| openclaw | openclaw | to 2026.2.6 (inc) |
Helpful Resources
Exploitability
| CWE ID | Description |
|---|---|
| CWE-94 | The product constructs all or part of a code segment using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify the syntax or behavior of the intended code segment. |
Attack-Flow Graph
AI Powered Q&A
Can you explain this vulnerability to me?
CVE-2026-30741 is a remote code execution (RCE) vulnerability in the OpenClaw Agent Platform version v2026.2.6 and earlier. It occurs due to a request-side prompt injection attack where the system lacks integrity validation for upstream API requests. This allows attackers to poison the request stream, manipulating high-performance models to generate unauthorized terminal commands. These commands are executed through MCP tools without requiring human confirmation, enabling attackers to run arbitrary code remotely on the affected system.
How can this vulnerability impact me? :
This vulnerability can have severe impacts as it allows remote attackers to execute arbitrary commands on the affected system without needing human confirmation. This can lead to unauthorized control over the system, potential data breaches, system compromise, and disruption of services. Attackers could leverage this to install malware, steal sensitive information, or disrupt operations.
How does this vulnerability affect compliance with common standards and regulations (like GDPR, HIPAA)?:
I don't know
How can this vulnerability be detected on my network or system? Can you suggest some commands?
The CVE-2026-30741 vulnerability is caused by request-side prompt injection that allows remote code execution via manipulated API requests. Detection involves monitoring for unusual or unauthorized terminal commands executed through MCP tools triggered by upstream API requests.
A proof of concept (PoC) demonstrating the attack is available, which may help in crafting detection signatures or commands.
Specific commands are not provided in the available resources, but detection could focus on logging and analyzing API request contents for suspicious prompt injections and monitoring execution logs of MCP tools for unexpected commands.
What immediate steps should I take to mitigate this vulnerability?
Immediate mitigation should focus on preventing request-stream poisoning by implementing integrity validation for upstream API requests to block malicious prompt injections.
Since the vulnerability allows execution of arbitrary commands without human confirmation, restricting or disabling automatic execution of commands from API requests until a patch is available is advisable.
Monitoring and restricting access to MCP tools and ensuring that only trusted sources can send API requests may reduce the attack surface.