AI agent vulnerability · OpenClaw

GHSA-m563-373q-885c: Duplicate Advisory: OpenClaw: OpenShell `mirror` mode can convert untrusted sandbox files into explicitly enabled workspace hooks and execute them on the host during gateway startup

mediumCVSS 4.0 5.4 · 3.1 7.3

This advisory was withdrawn on May 4, 2026. The publisher no longer considers it a valid vulnerability.

Duplicate Advisory This advisory has been withdrawn because it is a duplicate of GHSA-42mx-vp8m-j7qh. This link is maintained to preserve external references. Original Description OpenShell before 2026.3.28 contains an arbitrary code execution vulnerability in mirror mode that converts untrusted sandbox files into workspace hooks.

Published Apr 24, 2026 · Updated May 4, 2026

Affected packages

openclaw

Ecosystem: npm
Affected: < 2026.3.28
Fixed in: 2026.3.28
Check: npm ls openclaw

Advisory details

From the GitHub Advisory Database (CC BY 4.0).

Duplicate Advisory

This advisory has been withdrawn because it is a duplicate of GHSA-42mx-vp8m-j7qh. This link is maintained to preserve external references.

Original Description

OpenShell before 2026.3.28 contains an arbitrary code execution vulnerability in mirror mode that converts untrusted sandbox files into workspace hooks. Attackers with mirror mode access can execute arbitrary code on the host during gateway startup by exploiting enabled workspace hooks.

References

How this page is made: the data panel comes from the GitHub Advisory Database, CISA’s KEV catalog, the NVD and FIRST EPSS, and updates twice a day. No analysis has been written for this entry yet. Methodology

More OpenClaw vulnerabilities

All OpenClaw entries