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.
Weakness
The code transmits data to another actor, but a portion of the data includes sensitive information that should not be accessible to that actor.
Affected Software
| Name | Vendor | Start Version | End Version |
|---|---|---|---|
| Theia | Eclipse | * | 1.71.0 (excluding) |
Potential Mitigations
- Compartmentalize the system to have “safe” areas where trust boundaries can be unambiguously drawn. Do not allow sensitive data to go outside of the trust boundary and always be careful when interfacing with a compartment outside of the safe area.
- Ensure that appropriate compartmentalization is built into the system design, and the compartmentalization allows for and reinforces privilege separation functionality. Architects and designers should rely on the principle of least privilege to decide the appropriate time to use privileges and the time to drop privileges.
Related Attack Patterns
- https://cwe.mitre.org/data/definitions/12.html
- https://cwe.mitre.org/data/definitions/217.html
- https://cwe.mitre.org/data/definitions/612.html
- https://cwe.mitre.org/data/definitions/613.html
- https://cwe.mitre.org/data/definitions/618.html
- https://cwe.mitre.org/data/definitions/619.html
- https://cwe.mitre.org/data/definitions/621.html
- https://cwe.mitre.org/data/definitions/622.html
- https://cwe.mitre.org/data/definitions/623.html