Openclaw cli: OpenClaw log poisoning (indirect prompt injection) via WebSocket headers
Affects openclaw-cliSource GCVE Database
CVSS 3.1 Low : upgrade to 2026.2.13 when convenient.
Data as of 13 Nov 2026, 21:02 UTC
- Patch
- Available – fixed in 2026.2.13
CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:N/I:L/A:NWhat to do
Upgrade openclaw-cli to 2026.2.13.
Affected software
| Product | Affected | Fixed in |
|---|---|---|
Homebrewopenclaw-clipkg:brew/openclaw-cliOther threats | 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
Upgrade to openclaw version 2026.2.13 or later where the issue is fixed. Until then, treat logs as untrusted input when using AI-assisted debugging by sanitizing or escaping log content and avoid auto-executing instructions derived from logs. Additionally, restrict gateway network exposure and apply reverse-proxy limits on header size to reduce risk.
Description
OpenClaw CLI versions prior to 2026.2.13 log certain WebSocket request headers without sanitization or length limits when connections close before completing the handshake. This can allow unauthenticated clients to inject crafted header values into logs. If these logs are later processed by AI-assisted debugging tools or LLMs, this may lead to indirect prompt injection (log poisoning). The issue is fixed in version 2026.2.13 by sanitizing and truncating header values before logging.
References
- github.com/openclaw/openclaw/security/advisories/GHSA-g27f-9qjv-22pm (opens in a new tab)
- github.com/openclaw/openclaw/pull/15592 (opens in a new tab)
- github.com/openclaw/openclaw/commit/d637a263505448bf4505b85535babbfaacedbaac (opens in a new tab)
- github.com/openclaw/openclaw (opens in a new tab)
- github.com/openclaw/openclaw/releases/tag/v2026.2.13 (opens in a new tab)