CVE-2026-100537: OpenClaw before 2026.8.1 Authentication Bypass via Active Memory
OpenClaw (npm package 'openclaw') before 2026.8.1 fails to apply the originating requester's effective tool policy during Active Memory automatic recall. In deployments that use Active Memory together with requester-specific tool rules, deterministic and hidden recall paths can retrieve durable memory and inject it into the agent's context even when toolsBySender explicitly denies that requester access to the memory tools (memorysearch, memoryget). As a result, an admitted but denied sender can receive information derived from durable memory in the agent's response without directly invoking any memory tool. The issue is fixed in 2026.8.1.
Affected Software
Remediation
Recommended actions to resolve this vulnerability, in priority order.
- Upgrade
Upgrade
openclawto a version that resolves this vulnerability.Fixed in 2026.8.1
Event History
Frequently Asked Questions
Which deployments are exposed to this issue?
Deployments are affected when they use Active Memory together with requester-specific tool rules, and toolsBySender denies a requester access to memory_search or memory_get. An admitted sender subject to those denials may still receive information derived from durable memory through automatic recall.
What must an attacker be able to do to exploit it?
The attacker must be an admitted sender and be able to submit requests to the agent. They do not need to invoke memory_search or memory_get directly; deterministic or hidden Active Memory recall paths can place durable-memory content into the agent context.
How can this be remediated?
Upgrade OpenClaw to version 2026.8.1 or later. The issue is fixed in 2026.8.1.