CVE-2026-32898

Published: Mar 21, 2026 Last Modified: Mar 21, 2026
ExploitDB:
Other exploit source:
Google Dorks:
MEDIUM 5,3
Attack Vector: network
Attack Complexity: low
Privileges Required: low
User Interaction: none
Confidentiality: N/A
Integrity: N/A
Availability: N/A
MEDIUM 5,4
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

Incomplete
Common 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
View CWE Details
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…