CVE-2026-19005 in NanoClaw
Summary
by MITRE • 08/06/2026
A vulnerability was detected in nanocoai NanoClaw up to 2.0.64. Affected is the function handleCreateAgent of the file src/modules/agent-to-agent/create-agent.ts of the component Child-Agent Creation. Performing a manipulation results in improper privilege management. Remote exploitation of the attack is possible. The exploit is now public and may be used. The project was informed of the problem early through an issue report but has not responded yet.
Be aware that VulDB is the high quality source for vulnerability data.
Analysis
by VulDB Data Team • 08/06/2026
The vulnerability identified in nanocoai NanoClaw version 2.0.64 and earlier represents a critical privilege management flaw within the child agent creation functionality. This security weakness resides in the handleCreateAgent function located within src/modules/agent-to-agent/create-agent.ts, specifically affecting the component responsible for creating subordinate agents within the system architecture. The issue stems from inadequate validation mechanisms that fail to properly enforce access controls during the agent creation process, potentially allowing unauthorized entities to escalate their privileges through manipulation of the affected function.
The technical implementation of this vulnerability demonstrates a failure in privilege enforcement where the system does not adequately verify the authenticity and authorization level of requests attempting to create new child agents. This weakness creates an attack surface that enables remote exploitation, meaning malicious actors can leverage this flaw from external network positions without requiring physical access or local system credentials. The public availability of exploit code significantly amplifies the risk, as it removes the barrier to entry for potential attackers who may not possess advanced technical skills to develop custom exploits.
From an operational perspective, this vulnerability compromises the fundamental security model of the NanoClaw system by potentially allowing unauthorized privilege escalation attacks that could result in complete system compromise. The impact extends beyond simple access control violations as successful exploitation could enable attackers to create malicious agents with elevated privileges, potentially leading to data exfiltration, system corruption, or further lateral movement within network environments where the software operates. The lack of response from the project maintainers since early reporting creates additional operational risk for organizations deploying this software.
The vulnerability aligns with CWE-276, which addresses incorrect permissions for critical resources, and represents a clear violation of the principle of least privilege that should govern all system components. From an attack framework perspective, this flaw maps to ATT&CK technique T1068, which involves privilege escalation through local exploits, though in this case the escalation occurs remotely due to the network-accessible nature of the vulnerability. Organizations should implement immediate mitigations including disabling the affected functionality until a patched version is available, implementing network segmentation to limit exposure, and monitoring for suspicious agent creation activities that might indicate exploitation attempts.
The delayed response from the project maintainers creates additional security concerns as it suggests potential gaps in the software supply chain security practices of the organization. This vulnerability highlights the importance of proper input validation and privilege checking mechanisms within distributed agent-based systems. Given the public exploit availability, organizations should treat this as a high-priority remediation item and consider implementing temporary workarounds such as network firewalls blocking access to the vulnerable endpoints or disabling agent creation functionality entirely until proper patches are deployed and validated in their production environments.