OpenClaw versions prior to 2026.2.23 contain a sandbox bypass vulnerability in the sandboxed image tool that fails to enforce tools.fs.workspaceOnly restrictions on mounted sandbox paths, allowing attackers to read out-of-workspace files. Attackers can load restricted mounted images and exfiltrate them through vision model provider requests to bypass sandbox confidentiality controls.
Attack Parameters
Attack Vector
Network
Can be exploited remotely
Attack Complexity
High
Difficult to exploit
Attack Requirements
None
No additional conditions
Privileges Required
Low
Basic privileges needed
User Interaction
None
No user interaction needed
Impact Assessment
Confidentiality
High
Complete data leak
Integrity
None
No data modification
Availability
None
No disruption
CVSS Vector v4.0
Weakness Type (CWE)
Vulnerable Products 1
| Configuration | From (including) | Up to (excluding) |
|---|---|---|
|
Openclaw Openclaw
cpe:2.3:a:openclaw:openclaw:*:*:*:*:*:node.js:*:*
|
— |
2026.2.23
|
References 3
https://github.com/openclaw/openclaw/commit/dd9d9c1c609dcb4579f9e57bd7b5c879d01…
disclosure@vulncheck.com
https://github.com/openclaw/openclaw/security/advisories/GHSA-q6qf-4p5j-r25g
disclosure@vulncheck.com
https://www.vulncheck.com/advisories/openclaw-sandbox-boundary-bypass-via-image…
disclosure@vulncheck.com