Summary
[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.
Impact
Affected versions
Security releases
Kodem intelligence
Severity tells you how bad this could be in the worst case. It does not tell you whether you are exposed. Exploitability and impact are functions of runtime truth: whether the vulnerable code is present, reachable, and actually executes in your application. A vulnerable package can sit in your dependency tree and never run.
Kodem, an Intelligent Application Security platform, uses runtime intelligence to reveal which vulnerabilities actually execute in production, so teams prioritize the ones that genuinely matter. Kodem's runtime-powered SCA identifies whether this CVE is reachable in your applications.
Already deployed Kodem?
See it in your environmentNew to Kodem? Get a demo →Remediation advice
@theia/ai-chat-ui to 1.71.0 or later; @theia/ai-chat to 1.71.0 or later; @theia/ai-claude-code to 1.71.0 or later; @theia/ai-code-completion to 1.71.0 or later; @theia/ai-core to 1.71.0 or later; @theia/ai-editor to 1.71.0 or later; @theia/ai-ide to 1.71.0 or later
Kodem Kai can prioritize this vulnerability in your dependency tree and generate a fix recommendation.
Frequently Asked Questions
- What is CVE-2026-44688? CVE-2026-44688 is a high-severity security vulnerability in @theia/ai-chat-ui (npm), affecting versions < 1.71.0. It is fixed in 1.71.0.
- Which packages are affected by CVE-2026-44688?
@theia/ai-chat-ui(npm) (versions < 1.71.0)@theia/ai-chat(npm) (versions < 1.71.0)@theia/ai-claude-code(npm) (versions < 1.71.0)@theia/ai-code-completion(npm) (versions < 1.71.0)@theia/ai-core(npm) (versions < 1.71.0)@theia/ai-editor(npm) (versions < 1.71.0)@theia/ai-ide(npm) (versions < 1.71.0)
- Is there a fix for CVE-2026-44688? Yes. CVE-2026-44688 is fixed in 1.71.0. Upgrade to this version or later.
- Is CVE-2026-44688 exploitable, and should I be worried? Whether CVE-2026-44688 is exploitable in your environment depends on whether the vulnerable code is present and reachable. A CVSS score is a worst-case rating; it does not account for your specific deployment, configuration, or usage patterns. Kodem, an Intelligent Application Security platform, uses runtime intelligence to show which vulnerabilities actually execute in production, so you can focus on the ones that represent real risk. Get a demo
- What actually determines whether CVE-2026-44688 is exploitable, and how bad it is? Exploitability and impact are not fixed properties of a CVE. They depend on runtime truth: whether the vulnerable code is present, reachable, and actually executes in your application. A high CVSS score on a dependency that never runs is not the same as real risk. Kodem, an Intelligent Application Security platform, uses runtime intelligence to reveal which vulnerabilities actually execute in production, so teams prioritize the ones that genuinely matter.
- How do I fix CVE-2026-44688?
- Upgrade
@theia/ai-chat-uito 1.71.0 or later - Upgrade
@theia/ai-chatto 1.71.0 or later - Upgrade
@theia/ai-claude-codeto 1.71.0 or later - Upgrade
@theia/ai-code-completionto 1.71.0 or later - Upgrade
@theia/ai-coreto 1.71.0 or later - Upgrade
@theia/ai-editorto 1.71.0 or later - Upgrade
@theia/ai-ideto 1.71.0 or later
- Upgrade