CVE-2026-100537
LOW
2,3
Source: [email protected]
Attack Vector: network
Attack Complexity: high
Privileges Required: low
User Interaction: none
Confidentiality: N/A
Integrity: N/A
Availability: N/A
LOW
3,1
Source: [email protected]
Attack Vector: network
Attack Complexity: high
Privileges Required: low
User Interaction: none
Scope: unchanged
Confidentiality: low
Integrity: none
Availability: none
Description
AI Translation Available
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 (memory_search, memory_get). 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.
862
Missing Authorization
IncompleteCommon Consequences
Security Scopes Affected:
Confidentiality
Integrity
Access Control
Availability
Potential Impacts:
Read Application Data
Read Files Or Directories
Modify Application Data
Modify Files Or Directories
Gain Privileges Or Assume Identity
Bypass Protection Mechanism
Dos: Crash, Exit, Or Restart
Dos: Resource Consumption (Cpu)
Dos: Resource Consumption (Memory)
Dos: Resource Consumption (Other)
Applicable Platforms
Technologies:
AI/ML, Web Server, Database Server, Not Technology-Specific
https://github.com/openclaw/openclaw/security/advisories/GHSA-wjfv-5qch-m5vj
https://www.vulncheck.com/advisories/openclaw-before-2026.8.1-authentication-by…