[Eclipse Theia] Data Exfiltration via Markdown Image Rendering in AI Chat
Eclipse Foundation Eclipse Theia
Affected versions
| Product | Affected | Fixed in |
|---|---|---|
| @theia/ai-chat-ui npm |
|
|
| @theia/ai-chat npm |
|
|
| @theia/ai-claude-code npm |
Eclipse Foundation Eclipse Theia
| Product | Affected | Fixed in |
|---|---|---|
| @theia/ai-chat-ui npm |
|
|
| @theia/ai-chat npm |
|
|
| @theia/ai-claude-code npm |
< 1.71.0
|
| @theia/ai-code-completion npm |
|
|
| @theia/ai-core npm |
|
|
| @theia/ai-editor npm |
|
|
| @theia/ai-ide npm |
|
|
In Eclipse Theia versions prior to 1.71.0, the AI chat rendered Markdown image tags from AI responses, triggering HTTP requests to arbitrary external URLs without restriction. Combined with prompt injection in a malicious workspace, an attacker could induce the AI agent to construct image URLs encoding sensitive information from the workspace or conversation context, exfiltrating it to attacker-controlled servers. The workspace trust enforcement introduced in v1.71.0 mitigates the documented attack chain by disabling AI features in untrusted workspaces.
From the CVE record · eclipse
Before 1.71.0, Eclipse Theia AI chat rendered Markdown images from AI responses, making HTTP requests to arbitrary external URLs. An attacker using prompt injection in a malicious workspace could cause the AI agent to place sensitive workspace or conversation data in image URLs sent to an attacker-controlled server.
Teams running Eclipse Theia before 1.71.0 or the affected @theia/ai-* npm packages before 1.71.0 should check their installations.