Skip to content
Fencer Vulns
high 8.8

CVE-2026-44688 json

[Eclipse Theia] Indirect Prompt Injection via Adversarial Workspace File and Directory Names in AI Chat

published 2026-06-18 4 mo ago modified 2026-10-26 14 d ago also EUVD-2026-37898 , GHSA-3jww-hxqj-wfq2

cvss
8.8
version 3.1, NVD
cisa kev
Not listed
not in CISA's catalog
epss
0.5%
EPSS 0.5% chance of exploitation in 30 days, percentile 43%
public exploits
0
none known

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 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.

Patch / fix

  • npm @theia/ai-chat-ui 1.71.0
  • npm @theia/ai-chat 1.71.0
  • npm @theia/ai-claude-code 1.71.0
  • npm @theia/ai-code-completion 1.71.0
  • npm @theia/ai-core 1.71.0
  • npm @theia/ai-editor 1.71.0
  • npm @theia/ai-ide 1.71.0
  • Eclipse Foundation Eclipse Theia 1.71.0

CISA SSVC

Exploitation
none
Automatable
no
Technical impact
total
Assessed
4 mo ago

Exploit prediction

0.51% chance of exploitation in the next 30 days, higher than 43% of all scored CVEs (FIRST EPSS, 2026-11-08).

CVSS scores

assigned by version score vector
CNA 4.0 8.4 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
CNA 4.0 8.4 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/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
NVD 3.1 8.8 CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H

Affected packages

ecosystem package affected fixed in
npm @theia/ai-chat-ui
<1.71.0
1.71.0
npm @theia/ai-chat
<1.71.0
1.71.0
npm @theia/ai-claude-code
<1.71.0
1.71.0
npm @theia/ai-code-completion
<1.71.0
1.71.0
npm @theia/ai-core
<1.71.0
1.71.0
npm @theia/ai-editor
<1.71.0
1.71.0
npm @theia/ai-ide
<1.71.0
1.71.0

Affected products

  • Eclipse Foundation Eclipse Theia

Classification

Weakness
  • CWE-1427 Improper Neutralization of Input Used for LLM Prompting
  • CWE-829 Inclusion of Functionality from Untrusted Control Sphere

References

Sources

Fencer Vulns keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.

CPEs and fixed versions use Anchore's correction of NVD's data: Added CPE configurations because not yet analyzed by NVD.