OpenClaw: message.action forwarding could send Gateway credentials to model-supplied loopback URLs
Affects openclawSource GCVE Database
CVSS 6.8 Medium : upgrade to 2026.5.2 when convenient.
Data as of 2 Jul 2026, 23:20 UTC
- Patch
- Available – fixed in 2026.5.2
CVSS:4.0/AV:L/AC:L/AT:N/PR:L/UI:N/VC:H/VI:N/VA:N/SC:N/SI:N/SA:NWhat to do
Upgrade openclaw to 2026.5.2.
Affected software
| Product | Affected | Fixed in |
|---|---|---|
| npmopenclaw | Affected
| Fixed in
|
Check your own hosts for these packages with threat-finder (opens in a new tab), our free open-source scanner.
AI-suggested
A fix is available in OpenClaw version 2026.5.2. Until patched, restrict message.action forwarding and avoid using model-supplied loopback targets. Additionally, narrow channel and tool allowlists, avoid sharing a Gateway between mutually untrusted users, and disable the affected feature when not needed to reduce risk.
Description
OpenClaw versions prior to 2026.5.2 have a vulnerability where message.action forwarding can send Gateway credentials to model-supplied loopback URLs. This occurs when model-controlled action metadata selects a loopback Gateway URL, causing the action payload and credentials to be forwarded to that URL. The vulnerability is limited to the named feature and configuration and does not affect the overall trusted-operator model. Exploitation depends on the operator's configuration and whether untrusted input can reach the affected path. The issue is patched in version 2026.5.2.