LobsterAI vulnerabilities

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.

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.

A vulnerability has been discovered in netease-youdao LobsterAI (versions 2026.6.15, 2026.8.28, 2026.9.3, 2026.9.4) in the function OpenClawConfigSync.buildBrowserConfig, leading to server-side request forgery. The attack can be launched remotely, and the exploit has been publicly released.

A flaw has been found in netease-youdao LobsterAI 2026.6.10, affecting the function parseMediaTokensFromText in the file src/renderer/services/artifactParser.ts in the MEDIA Path Handler component. This manipulation causes information disclosure. The attack is possible to be carried out remotely, and the exploit has been published.