Skip to content
OpenAdvisories

Package · npm

@theia/ai-ide

2 known vulnerabilities.

1 result · Clear filters · Feed

  • High 8.4

    [Eclipse Theia] Indirect Prompt Injection via Adversarial Workspace File and Directory Names in AI Chat

    In Eclipse Theia versions prior to 1.71.0, the AI chat agent processed workspace file and directory names as part of its prompt context without distinguishing them from system instructions. An attacker could craft a malicious repository with adversarial direc…