CVE-2026-44688

highpriority · track · 35EPSS 0.005 · 43 %ileEUUS

grimoire priorityP2 · Scheduled

Exploitable?

—

no known exploitation

Likely / severe?

0.51% (43rd) EPSS

CVSS 8.8 · high

Is it mine?

9 products

Check your exposure

Who says so?

4 sources

cnnvd · enisa_euvd · nvd · osv

EPSS · scored 2026-10-27

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.

cvss

Technical severity, 0–10. One row per scoring source.

8.8

010

base score 0–10 · higher = more severe · hover a vector to decode⚠ sources disagree · medium–high · 5.7–8.8

v3.18.8highCVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:Hprimary · NVD / NIST USexploitability 2.8 · impact 5.9

v4.08.4highCVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:A/VC:H/VI:H/VA:H/SC:N/SI:N/SA:Nsecondary · ENISA EU

v4.08.4highCVSS: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:Xsecondary · emo@eclipse.org

v4.05.7mediumCVSS: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:U/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:Xsecondary · CVSS-BT (t0sche)

ssvc

A stakeholder decision — act, attend, or track — from exploitation and impact.

Exploitation: none · Automatable: no · Technical Impact: totalcoordinatorcisa_ssvcUS

weaknesses

The CWE weakness classes this flaw belongs to.

CWE-829USCWE-829US

affected products (9)

Products and version ranges known to be affected.

Eclipse Foundation Eclipse Theia0 → 1.71.0enisa_euvdEU
eclipse theia< 1.71.0nvdUScpe:2.3:a:eclipse:theia:*:*:*:*:*:*:*:*
npm @theia/ai-chat< 1.71.0osvUSpkg:npm/%40theia/ai-chat
npm @theia/ai-chat-ui< 1.71.0osvUSpkg:npm/%40theia/ai-chat-ui
npm @theia/ai-claude-code< 1.71.0osvUSpkg:npm/%40theia/ai-claude-code
npm @theia/ai-code-completion< 1.71.0osvUSpkg:npm/%40theia/ai-code-completion
npm @theia/ai-core< 1.71.0osvUSpkg:npm/%40theia/ai-core
npm @theia/ai-editor< 1.71.0osvUSpkg:npm/%40theia/ai-editor
npm @theia/ai-ide< 1.71.0osvUSpkg:npm/%40theia/ai-ide

advisories (1)

Vendor and ecosystem advisories describing this.

GHSA-3jww-hxqj-wfq2[Eclipse Theia] Indirect Prompt Injection via Adversarial Workspace File and Directory Names in AI Chat2026-06-18ghsa · osvUS
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.

also known as (3)

Other names and identifiers for this entity.

sources

Which sources assert this record, and when.

cnnvd enisa_euvd nvd osv NVD CVE.org MITRE

published 2026-06-18modified 2026-10-26

references (4)

External citations — patches, advisories, analysis.

scry

Attackers weaponise vulnerabilities like this against internet-exposed services. See what is exposed on your perimeter with a free passive scan.

Free scan