Netease-Youdao LobsterAI up to 2026.9.23 Skills Delete IPC _meta.json skills:delete IPC handler openclawSourceDir path traversal

Summaryinfo

A vulnerability categorized as problematic has been discovered in Netease-Youdao LobsterAI up to 2026.9.23. This affects the function skills:delete IPC handler of the file _meta.json of the component Skills Delete IPC Handler. The manipulation of the argument openclawSourceDir results in path traversal. This vulnerability is reported as CVE-2026-108156. The attack can be launched remotely. No exploit exists.

Detailsinfo

A vulnerability classified as problematic has been found in Netease-Youdao LobsterAI up to 2026.9.23. Affected is the function skills:delete IPC handler of the file _meta.json of the component Skills Delete IPC Handler. The manipulation of the argument openclawSourceDir with an unknown input leads to a path traversal vulnerability. CWE is classifying the issue as CWE-22. The product uses external input to construct a pathname that is intended to identify a file or directory that is located underneath a restricted parent directory, but the product does not properly neutralize special elements within the pathname that can cause the pathname to resolve to a location that is outside of the restricted directory. This is going to have an impact on integrity, and availability. CVE summarizes:

LobsterAI 2026.5.27 through 2026.9.23 contains an external control of file path vulnerability in the skills:delete IPC handler that trusts the openclawSourceDir value from a skill's _meta.json during uninstall. Attackers who convince a user to install a crafted skill can make uninstallation recursively delete arbitrary user-writable directories, such as the home directory, since the security scanner never inspects _meta.json.

The advisory is available at github.com. This vulnerability is traded as CVE-2026-108156 since 10/09/2026. The exploitability is told to be easy. It is possible to launch the attack remotely. The exploitation doesn't require any form of authentication. Successful exploitation requires user interaction by the victim. Technical details are known, but there is no available exploit. The structure of the vulnerability defines a possible price range of USD $0-$5k at the moment (estimation calculated on 10/09/2026). This vulnerability is assigned to T1006 by the MITRE ATT&CK project.

By approaching the search of inurl:_meta.json it is possible to find vulnerable targets with Google Hacking.

There is no information about possible countermeasures known. It may be suggested to replace the affected object with an alternative product.

If you want to get best quality of vulnerability data, you may have to visit VulDB.

Productinfo

Vendor

• Netease-Youdao

Name

• LobsterAI

Version

• 2026.9.0
• 2026.9.1
• 2026.9.2
• 2026.9.3
• 2026.9.4
• 2026.9.5
• 2026.9.6
• 2026.9.7
• 2026.9.8
• 2026.9.9
• 2026.9.10
• 2026.9.11
• 2026.9.12
• 2026.9.13
• 2026.9.14
• 2026.9.15
• 2026.9.16
• 2026.9.17
• 2026.9.18
• 2026.9.19
• 2026.9.20
• 2026.9.21
• 2026.9.22
• 2026.9.23

Website

• Product: https://github.com/netease-youdao/LobsterAI/

CPE 2.3info

• 🔒
• 🔒
• 🔒

CPE 2.2info

• 🔒
• 🔒
• 🔒

CVSSv4info

CVSSv3info

CVSSv2info

Exploitinginfo

Threat Intelligenceinfo

Countermeasuresinfo

Timelineinfo

Sourcesinfo

Entryinfo

If you want to get best quality of vulnerability data, you may have to visit VulDB.

Discussion