CVE-2026-44688
HighCVSS 8.8Exploitation Probability (EPSS)
Low risk19th percentile — higher than 19% of all known CVEs
Summary
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, leading to the execution of attacker-controlled instructions.
Risk Assessment
This vulnerability could lead to data exfiltration via Markdown image rendering or arbitrary command execution via task definitions, posing a significant security risk to the organization.
Recommendation
It is recommended to update Eclipse Theia to version 1.71.0 or later and review security policies regarding trusted and untrusted workspaces.
Original NVD description (English source)
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.