@theia/ai-chat-ui (>=1.46.0-next.241, <=1.70.2), @theia/ai-claude-code (>=1.65.0, <=1.70.2) +8 more potentially affected by CVE-2026-22551 via @theia/ai-chat (>=1.46.0-next.241, <=1.70.2)

@theia/ai-chat NPM version =1.46.0-next.241, =1.46.0-next.241, =1.65.0, =1.67.0-next.56, =0.0.1, =1.62.0, =1.59.0-next.62, =1.57.0-next.37, =1.46.0-next.241, =1.46.0-next.241, =1.58.5 Source cves: CVE-2026-22551 Source advisory: SNYK:JS-THEIAAICHAT-17391864...

@theia/ai-claude-code (>=1.65.0, <=1.70.2), @theia/ai-codex (>=1.67.0-next.56, <=1.70.2) +5 more potentially affected by CVE-2026-22551 via @theia/ai-chat-ui (>=1.57.0, <=1.70.2)

@theia/ai-chat-ui NPM version =1.57.0, =1.65.0, =1.67.0-next.56, =1.63.0, =1.62.0, =1.60.0-next.43, =1.57.0-next.37, =1.68.0-next.79, =1.70.2 Source cves: CVE-2026-22551 Source advisory: OSV:GHSA-QWJM-9C66-W4Q4...

@theia/ai-claude-code (>=1.65.0, <=1.70.2), @theia/ai-codex (>=1.67.0-next.56, <=1.70.2) +5 more potentially affected by CVE-2026-44688 via @theia/ai-chat-ui (>=1.57.0, <=1.70.2)

@theia/ai-chat-ui NPM version =1.57.0, =1.65.0, =1.67.0-next.56, =1.63.0, =1.62.0, =1.60.0-next.43, =1.57.0-next.37, =1.68.0-next.79, =1.70.2 Source cves: CVE-2026-44688 Source advisory: OSV:GHSA-3JWW-HXQJ-WFQ2...

@theia/ai-chat-ui (>=1.46.0-next.241, <=1.70.2), @theia/ai-claude-code (>=1.65.0, <=1.70.2) +8 more potentially affected by CVE-2026-44688 via @theia/ai-chat (>=1.46.0-next.241, <=1.70.2)

@theia/ai-chat NPM version =1.46.0-next.241, =1.46.0-next.241, =1.65.0, =1.67.0-next.56, =0.0.1, =1.62.0, =1.59.0-next.62, =1.57.0-next.37, =1.46.0-next.241, =1.46.0-next.241, =1.58.5 Source cves: CVE-2026-44688 Source advisory: OSV:GHSA-3JWW-HXQJ-WFQ2...

Unsafe Dependency Resolution

Overview @theia/ai-chat-ui is a Theia - AI Chat UI Extension Affected versions of this package are vulnerable to Unsafe Dependency Resolution via the processing of workspace file and directory names in the AI chat. An attacker can cause the agent to execute attacker-controlled instructions by...

GHSA-3JWW-HXQJ-WFQ2 [Eclipse Theia] Indirect Prompt Injection via Adversarial Workspace File and Directory Names in AI Chat

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...

Insertion of Sensitive Information Into Sent Data

Overview @theia/ai-ide is an AI IDE Agents Extension Affected versions of this package are vulnerable to Insertion of Sensitive Information Into Sent Data via the rendering of Markdown image tags in AI chat responses. An attacker can cause sensitive information from the workspace or conversation...

Insertion of Sensitive Information Into Sent Data

Overview @theia/ai-code-completion is a Theia - AI Core Affected versions of this package are vulnerable to Insertion of Sensitive Information Into Sent Data via the rendering of Markdown image tags in AI chat responses. An attacker can cause sensitive information from the workspace or conversati...

Unsafe Dependency Resolution

Overview @theia/ai-chat is a Theia - AI Chat Extension Affected versions of this package are vulnerable to Unsafe Dependency Resolution via the processing of workspace file and directory names in the AI chat. An attacker can cause the agent to execute attacker-controlled instructions by introduci...

@theia/ai-chat-ui (>=1.46.0-next.241, <=1.70.2), @theia/ai-claude-code (>=1.65.0, <=1.70.2) +8 more potentially affected by CVE-2026-22551 via @theia/ai-chat (>=1.46.0-next.241, <=1.70.2)

@theia/ai-chat NPM version =1.46.0-next.241, =1.46.0-next.241, =1.65.0, =1.67.0-next.56, =0.0.1, =1.62.0, =1.59.0-next.62, =1.57.0-next.37, =1.46.0-next.241, =1.46.0-next.241, =1.58.5 Source cves: CVE-2026-22551 Source advisory: OSV:GHSA-QWJM-9C66-W4Q4...

[Eclipse Theia] Data Exfiltration via Markdown Image Rendering in AI Chat

In Eclipse Theia versions prior to 1.71.0, the AI chat rendered Markdown image tags from AI responses, triggering HTTP requests to arbitrary external URLs without restriction. Combined with prompt injection in a malicious workspace, an attacker could induce the AI agent to construct image URLs...

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

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...

Insertion of Sensitive Information Into Sent Data

Overview @theia/ai-claude-code is a Theia - Claude Code Integration Affected versions of this package are vulnerable to Insertion of Sensitive Information Into Sent Data via the rendering of Markdown image tags in AI chat responses. An attacker can cause sensitive information from the workspace o...

CVE-2026-44691

In Eclipse Theia versions prior to 1.69.0, custom task definitions in workspace files e.g. .theia/tasks.json, .vscode/tasks.json could be executed without requiring workspace trust. An attacker could craft a malicious repository that, when cloned and opened in Theia, leads to execution of arbitra...

CVE-2026-44688

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...

CVE-2026-22551

In Eclipse Theia versions prior to 1.71.0, the AI chat rendered Markdown image tags from AI responses, triggering HTTP requests to arbitrary external URLs without restriction. Combined with prompt injection in a malicious workspace, an attacker could induce the AI agent to construct image URLs...

CVE-2026-22551

In Eclipse Theia versions prior to 1.71.0, the AI chat rendered Markdown image tags from AI responses, triggering HTTP requests to arbitrary external URLs without restriction. Combined with prompt injection in a malicious workspace, an attacker could induce the AI agent to construct image URLs...

CVE-2026-44691

In Eclipse Theia versions prior to 1.69.0, custom task definitions in workspace files e.g. .theia/tasks.json, .vscode/tasks.json could be executed without requiring workspace trust. An attacker could craft a malicious repository that, when cloned and opened in Theia, leads to execution of arbitra...

UBUNTU-CVE-2026-44688

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...

CVE-2026-44691

In Eclipse Theia versions prior to 1.69.0, custom task definitions in workspace files e.g. .theia/tasks.json, .vscode/tasks.json could be executed without requiring workspace trust. An attacker could craft a malicious repository that, when cloned and opened in Theia, leads to execution of arbitra...