GHSA-Q6QF-4P5J-R25G
Vulnerability from github – Published: 2026-03-04 19:13 – Updated: 2026-03-30 13:26Summary
In OpenClaw, the sandboxed image tool did not honor tools.fs.workspaceOnly=true for mounted paths resolved by the sandbox FS bridge. This allowed reading out-of-workspace mounted images (for example /agent/*) and forwarding those bytes to vision model providers.
Impact
Sandbox boundary bypass with confidentiality impact. In affected versions, read/write/edit respected workspace-only guardrails, but image could still load mounted out-of-workspace files and exfiltrate them via model requests.
Affected Packages / Versions
- Package:
openclaw(npm) - Affected versions:
<= 2026.2.22-2 - Patched versions:
>= 2026.2.23(released) - Latest published npm at triage time:
2026.2.22-2
Technical Details
workspaceOnly was enforced in sandbox file tools and apply_patch, but not propagated/enforced for image sandbox path resolution. The fix threads workspaceOnly into image-tool construction and asserts sandbox-root containment before loading media bytes.
Fix Commit(s)
dd9d9c1c609dcb4579f9e57bd7b5c879d0146b53
OpenClaw thanks @tdjackey for reporting.
{
"affected": [
{
"package": {
"ecosystem": "npm",
"name": "openclaw"
},
"ranges": [
{
"events": [
{
"introduced": "0"
},
{
"fixed": "2026.2.23"
}
],
"type": "ECOSYSTEM"
}
]
}
],
"aliases": [
"CVE-2026-32002"
],
"database_specific": {
"cwe_ids": [
"CWE-200",
"CWE-284"
],
"github_reviewed": true,
"github_reviewed_at": "2026-03-04T19:13:48Z",
"nvd_published_at": "2026-03-19T22:16:32Z",
"severity": "MODERATE"
},
"details": "### Summary\nIn OpenClaw, the sandboxed `image` tool did not honor `tools.fs.workspaceOnly=true` for mounted paths resolved by the sandbox FS bridge. This allowed reading out-of-workspace mounted images (for example `/agent/*`) and forwarding those bytes to vision model providers.\n\n### Impact\nSandbox boundary bypass with confidentiality impact. In affected versions, `read`/`write`/`edit` respected workspace-only guardrails, but `image` could still load mounted out-of-workspace files and exfiltrate them via model requests.\n\n### Affected Packages / Versions\n- Package: `openclaw` (npm)\n- Affected versions: `\u003c= 2026.2.22-2`\n- Patched versions: `\u003e= 2026.2.23` (released)\n- Latest published npm at triage time: `2026.2.22-2`\n\n### Technical Details\n`workspaceOnly` was enforced in sandbox file tools and `apply_patch`, but not propagated/enforced for `image` sandbox path resolution. The fix threads `workspaceOnly` into image-tool construction and asserts sandbox-root containment before loading media bytes.\n\n### Fix Commit(s)\n- `dd9d9c1c609dcb4579f9e57bd7b5c879d0146b53`\n\nOpenClaw thanks @tdjackey for reporting.",
"id": "GHSA-q6qf-4p5j-r25g",
"modified": "2026-03-30T13:26:46Z",
"published": "2026-03-04T19:13:48Z",
"references": [
{
"type": "WEB",
"url": "https://github.com/openclaw/openclaw/security/advisories/GHSA-q6qf-4p5j-r25g"
},
{
"type": "ADVISORY",
"url": "https://nvd.nist.gov/vuln/detail/CVE-2026-32002"
},
{
"type": "WEB",
"url": "https://github.com/openclaw/openclaw/commit/dd9d9c1c609dcb4579f9e57bd7b5c879d0146b53"
},
{
"type": "PACKAGE",
"url": "https://github.com/openclaw/openclaw"
},
{
"type": "WEB",
"url": "https://www.vulncheck.com/advisories/openclaw-sandbox-boundary-bypass-via-image-tool-workspaceonly-bypass"
}
],
"schema_version": "1.4.0",
"severity": [
{
"score": "CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:H/I:N/A:N",
"type": "CVSS_V3"
},
{
"score": "CVSS:4.0/AV:N/AC:H/AT:N/PR:L/UI:N/VC:H/VI:N/VA:N/SC:N/SI:N/SA:N",
"type": "CVSS_V4"
}
],
"summary": "OpenClaw\u0027s image tool bypasses tools.fs.workspaceOnly on sandbox mount paths and exfiltrates out-of-workspace images"
}
Sightings
| Author | Source | Type | Date |
|---|
Nomenclature
- Seen: The vulnerability was mentioned, discussed, or observed by the user.
- Confirmed: The vulnerability has been validated from an analyst's perspective.
- Published Proof of Concept: A public proof of concept is available for this vulnerability.
- Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
- Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
- Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
- Not confirmed: The user expressed doubt about the validity of the vulnerability.
- Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.