Before OpenClaw 2026.4.2, QQ Bot structured media payloads could read local files from attacker-chosen paths. A crafted structured payload could escape QQ Bot-owned media roots and cause arbitrary file reads on the host.
Prompt-influenced structured payload output could exfiltrate any host file readable by the OpenClaw process through the QQ Bot media-send path. This was a real confidentiality bug on the host filesystem boundary.
openclaw (npm)<= 2026.4.1>= 2026.4.22026.4.12c45b06afdd6f7c621038b5419d8e661cff34a7f — restrict QQ Bot structured payload local pathsThe fix is present on main and is staged for OpenClaw 2026.4.2. Publish this advisory after the 2026.4.2 npm release is live.
Thanks @feiyang666 of Tencent zhuque Lab (https://github.com/Tencent/AI-Infra-Guard) for reporting.
{
"cwe_ids": [
"CWE-22"
],
"github_reviewed": true,
"github_reviewed_at": "2026-04-07T18:15:00Z",
"nvd_published_at": null,
"severity": "MODERATE"
}