CVE-2026-44688

Affects: prompt injection

CVSS: HIGH · 8.8v3.1
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
Published: 2026-06-18
Weakness: CWE-829
Source: nvd.nist.gov/vuln/detail/CVE-2026-44688

Description

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.

References

https://gitlab.eclipse.org/security/cve-assignment/-/work_items/113

How GTK Cyber trains on this

AI security training at GTK Cyber covers the LLM and ML-pipeline vulnerability classes that vulnerabilities like CVE-2026-44688 fall into. Our hands-on courses are taught by Charles Givre and other practitioners who break and defend production AI systems.

AI Red-Teaming course →·Browse MITRE ATLAS techniques

Related AI/LLM CVEs

AI security training, taught by people who do the work.

Hands-on courses on adversarial AI, prompt injection, and ML pipeline security.

Explore AI Red-Teaming