CVE-2026-46580: CWE-829: Inclusion of Functionality from Untrusted Control Sphere in Eclipse Foundation Eclipse Theia
Eclipse Theia versions prior to 1.71.0 automatically load files matching the pattern .prompts/*.prompttemplate from a workspace, which can override or extend AI agent system prompts. This behavior allows an attacker to craft a malicious repository that replaces the AI's system instructions with attacker-controlled content, leading to indirect prompt injection. Exploitation combined with other AI chat features in untrusted workspaces can result in data exfiltration via Markdown image rendering or arbitrary command execution via task definitions. The vulnerability has a high severity with a CVSS score of 8.4.
AI Analysis
Technical Summary
CVE-2026-46580 is a vulnerability in Eclipse Theia prior to version 1.71.0 where files matching .prompts/*.prompttemplate in a workspace are automatically loaded and can override or extend AI system prompts. This allows an attacker to inject malicious prompt templates by providing a crafted repository. The indirect prompt injection can be leveraged with other AI chat features in untrusted workspaces to perform attack chains that lead to data exfiltration through Markdown image rendering or arbitrary command execution via task definitions. The vulnerability is categorized under CWE-829 (Inclusion of Functionality from Untrusted Control Sphere) and CWE-1427.
Potential Impact
An attacker who can supply a malicious workspace repository can replace AI system prompts with attacker-controlled content, enabling indirect prompt injection. This can lead to data exfiltration through Markdown image rendering or arbitrary command execution via task definitions, posing a significant risk to confidentiality and system integrity. The vulnerability requires user interaction (opening the workspace) and local access to the workspace files.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Until an official fix is available, avoid opening untrusted or suspicious workspaces in Eclipse Theia versions prior to 1.71.0. Restrict workspace sources to trusted repositories to prevent loading malicious prompt templates.
CVE-2026-46580: CWE-829: Inclusion of Functionality from Untrusted Control Sphere in Eclipse Foundation Eclipse Theia
Description
Eclipse Theia versions prior to 1.71.0 automatically load files matching the pattern .prompts/*.prompttemplate from a workspace, which can override or extend AI agent system prompts. This behavior allows an attacker to craft a malicious repository that replaces the AI's system instructions with attacker-controlled content, leading to indirect prompt injection. Exploitation combined with other AI chat features in untrusted workspaces can result in data exfiltration via Markdown image rendering or arbitrary command execution via task definitions. The vulnerability has a high severity with a CVSS score of 8.4.
CVSS v4.0
Score 8.4high
Affected software
Run on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
CVE-2026-46580 is a vulnerability in Eclipse Theia prior to version 1.71.0 where files matching .prompts/*.prompttemplate in a workspace are automatically loaded and can override or extend AI system prompts. This allows an attacker to inject malicious prompt templates by providing a crafted repository. The indirect prompt injection can be leveraged with other AI chat features in untrusted workspaces to perform attack chains that lead to data exfiltration through Markdown image rendering or arbitrary command execution via task definitions. The vulnerability is categorized under CWE-829 (Inclusion of Functionality from Untrusted Control Sphere) and CWE-1427.
Potential Impact
An attacker who can supply a malicious workspace repository can replace AI system prompts with attacker-controlled content, enabling indirect prompt injection. This can lead to data exfiltration through Markdown image rendering or arbitrary command execution via task definitions, posing a significant risk to confidentiality and system integrity. The vulnerability requires user interaction (opening the workspace) and local access to the workspace files.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Until an official fix is available, avoid opening untrusted or suspicious workspaces in Eclipse Theia versions prior to 1.71.0. Restrict workspace sources to trusted repositories to prevent loading malicious prompt templates.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- eclipse
- Date Reserved
- 2026-05-22T07:47:58.202Z
- Cvss Version
- 4.0
- State
- PUBLISHED
- Remediation Level
- null
Threat ID: 6a340cacf198dc38c1059184
Added to database: 06/18/2026, 15:20:12 UTC
Last enriched: 06/25/2026, 21:33:53 UTC
Last updated: 08/02/2026, 19:17:59 UTC
Views: 74
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
External Links
Need more coverage?
Upgrade to Pro Console for AI refresh and higher limits.
For incident response and remediation, OffSeq services can help resolve threats faster.
Latest Threats
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.