Netease-youdao LobsterAI vulnerabilities

🔔 Create alert RSS Version checker

Published CVEs affecting Netease-youdao LobsterAI: 4 record(s), with affected versions and fixes.

CVE-2026-112014 Medium · 5.5 CWE-321 Oct 18, 2026

LobsterAI before 2026.10.16 Hardcoded Password in Provider API Key Export

LobsterAI before 2026.10.16 contains a hardcoded password vulnerability that allows attackers to decrypt exported provider API keys encrypted with the constant 'lobsterai-APP'. Attackers who obtain a providers export file can derive the AES-GCM key via PBKDF2 using the embedded salt and recover every third-party AI provider API key.

CVE-2026-108156 High · 7.1 CWE-73 Oct 9, 2026

LobsterAI 2026.5.27 through 2026.9.23 Arbitrary Directory Deletion via Skill _meta.json

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.

CVE-2026-90818 Medium · 4.3 CWE-918 Sep 14, 2026

netease-youdao LobsterAI Browser Network Configuration openclawConfigSync.ts OpenClawConfigSync.buildBrowserConfig server-side request forgery

A security flaw has been discovered in netease-youdao LobsterAI 2026.6.15/2026.8.28/2026.9.3/2026.9.4. Impacted is the function OpenClawConfigSync.buildBrowserConfig of the file src/main/libs/openclawConfigSync.ts of the component Browser Network Configuration. The manipulation results in server-side request forgery. It is possible to launch the attack remotely. The exploit has been released to the public and may be used for attacks. The reported GitHub issue was closed automatically due to inactivity.

CVE-2026-18995 Medium · 4.3 CWE-200 Aug 6, 2026

netease-youdao LobsterAI MEDIA Path artifactParser.ts parseMediaTokensFromText information disclosure

A flaw has been found in netease-youdao LobsterAI 2026.6.10. This affects the function parseMediaTokensFromText of the file src/renderer/services/artifactParser.ts of the component MEDIA Path Handler. This manipulation causes information disclosure. The attack is possible to be carried out remotely. The exploit has been published and may be used. The project was informed of the problem early through an issue report but has not responded yet.