CVE-2026-32898
MEDIUM
5,3
Source: [email protected]
Attack Vector: network
Attack Complexity: low
Privileges Required: low
User Interaction: none
Confidentiality: N/A
Integrity: N/A
Availability: N/A
MEDIUM
5,4
Source: [email protected]
Attack Vector: network
Attack Complexity: low
Privileges Required: low
User Interaction: none
Scope: unchanged
Confidentiality: low
Integrity: low
Availability: none
Description
AI Translation Available
OpenClaw versions prior to 2026.2.23 contain an authorization bypass vulnerability in the ACP client that auto-approves tool calls based on untrusted toolCall.kind metadata and permissive name heuristics. Attackers can bypass interactive approval prompts for read-class operations by spoofing tool metadata or using non-core read-like names to reach auto-approve paths.
807
Reliance on Untrusted Inputs in a Security Decision
IncompleteCommon Consequences
Security Scopes Affected:
Confidentiality
Access Control
Availability
Other
Potential Impacts:
Bypass Protection Mechanism
Gain Privileges Or Assume Identity
Varies By Context
Applicable Platforms
Technologies:
Not Technology-Specific, Web Based, Web Server
https://github.com/openclaw/openclaw/commit/12cc754332f9a7c92e158ce7644aa22df79…
https://github.com/openclaw/openclaw/commit/63dcd28ae0be2de1c75af09cc81841cebee…
https://github.com/openclaw/openclaw/security/advisories/GHSA-7jx5-9fjg-hp4m
https://www.vulncheck.com/advisories/openclaw-acp-permission-auto-approval-bypa…