[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 directory or file names that, when analyzed by the AI agent, would cause the agent to follow attacker-controlled instructions (indirect prompt injection). Combined with other AI chat features available in untrusted workspaces, this enabled attack chains leading to data exfiltration via Markdown image rendering or arbitrary command execution via task definitions.
Affected software
Click a technology to see all vulnerabilities affecting it.
| Platform | Package | Vulnerable versions | Fixed in |
|---|---|---|---|
| npm package | @theia/ai-chat | < 1.71.0 | 1.71.0 |
| npm package | @theia/ai-chat-ui | < 1.71.0 | 1.71.0 |
| npm package | @theia/ai-claude-code | < 1.71.0 | 1.71.0 |
| npm package | @theia/ai-code-completion | < 1.71.0 | 1.71.0 |
| npm package | @theia/ai-core | < 1.71.0 | 1.71.0 |
| npm package | @theia/ai-editor | < 1.71.0 | 1.71.0 |
| npm package | @theia/ai-ide | < 1.71.0 | 1.71.0 |
References
- https://nvd.nist.gov/vuln/detail/CVE-2026-44688
- https://github.com/eclipse-theia/theia/issues/16892
- https://github.com/eclipse-theia/theia/pull/17364
- https://github.com/eclipse-theia/theia/commit/e3fdfe6992389bc5fa611058d00c39d7408508ed
- https://github.com/eclipse-theia/theia
- https://gitlab.eclipse.org/security/cve-assignment/-/work_items/113
- CVSS vector
CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:A/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N- Weakness (CWE)
CWE-829- Platform
- npm
- Package
@theia/ai-chat, @theia/ai-chat-ui, @theia/ai-claude-code- Disclosed
- 18.06.2026
- Updated
- 11.10.2026 10:22
Sources and licenses
OSV / GitHub Advisory Database - GHSA-3jww-hxqj-wfq2 - CC BY 4.0
Vulnerability history: @theia/ai-ide
All published vulnerabilities of this package (npm package), newest first. Shows whether this is a one-off slip or a package that needs watching.
- Total entries
- 2
- First → latest
- 06.2026 06.2026
- Without a fix
- 0
- Exploited in attacks
- 0
Severity breakdown
- High 1
- Medium 1
Disclosures per year
- 2026: 2
-
[Eclipse Theia] Indirect Prompt Injection via Adversarial Workspace File and Directory Names in AI Chat this entry
Know which vulnerabilities affect your application
With the DockRay integration and software inventory enabled, DockRay checks reported component versions against known vulnerabilities and notifies you about confirmed matches. Coverage depends on the supported technology and available advisory data.