UTC
High

OpenClaw authorization bypass: operator.write can resolve exec approvals via chat.send -> /approve

CVE-2026-28473 · GHSA-mqpw-46fh-299h · published 2026-02-17 · updated 2026-03-06

Severity
High
CVSS score
7.2
Chance of exploitation (EPSS)
0.33%
Fixed in
2026.2.2
  • Exploitation No known exploitation
  • Automatable No
  • Technical impact Partial
  • CISA SSVC
What it is

If you give a client “chat/write” access to the gateway (operator.write) but you do not intend to let that client approve exec requests (operator.approvals), affected versions could still let that client approve/deny a pending exec approval by sending the /approve chat command. This is mainly relevant for shared or multi-client setups where different tokens are intentionally scoped differently. Single-operator installs are typically less impacted.

What to do

Upgrade openclaw to 2026.2.2 or later. If you start it from an MCP config with npx or uvx, pin that version so an old cached copy is not used.

Fixed in openclaw 2026.2.2. Fix commit(s): efe2a464afcff55bb5a95b959e6bd9ec0fef086e. Change: when /approve is invoked from gateway clients (webchat/internal channel), it now requires the requesting client to have operator.approvals (or operator.admin).

If you cannot upgrade yet

Upgrade to openclaw >= 2026.2.2. If you cannot upgrade: avoid issuing write-only device tokens to untrusted clients; disable text commands (commands.text=false) or restrict access to the webchat/control UI.

Affected
PackageRegistryAffectedFixed in
openclawnpm< 2026.2.22026.2.2

The impact, patch and workaround text comes from the advisory, shortened (GitHub Advisory Database, CC BY 4.0). Proof-of-concept and reproduction sections and code are left out; the original advisory has them.

Sources: GitHub Advisory Database, reviewed and malware advisories (CC BY 4.0, https://github.com/advisories); advisories published by Cursor (https://github.com/cursor/cursor/security/advisories); advisories published by OpenClaw (https://github.com/openclaw/openclaw/security/advisories); advisories published by vLLM (https://github.com/vllm-project/vllm/security/advisories); advisories published by Open WebUI (https://github.com/open-webui/open-webui/security/advisories); advisories published by n8n (https://github.com/n8n-io/n8n/security/advisories); advisories published by Flowise (https://github.com/FlowiseAI/Flowise/security/advisories); advisories published by Langflow (https://github.com/langflow-ai/langflow/security/advisories); advisories published by the MCP Python SDK project (https://github.com/modelcontextprotocol/python-sdk/security/advisories); advisories published by MLflow (https://github.com/mlflow/mlflow/security/advisories); CISA Known Exploited Vulnerabilities catalog (CC0). Data as of 2026-11-22. ShieldMap describes how each problem works and how to fix it; it does not publish exploit code. Report a correction to [email protected].