Your RSA-2048 keys break in 2030. Find every one of them before attackers do.
📦 npm
Not in CISA KEV

CVE-2026-46580

CVE-2026-46580 is a CWE-829 vulnerability in @theia/ai-chat-ui. O3 Security confirms whether CVE-2026-46580 is actually reachable in your code before you act, and blocks exploitation at runtime until you patch.

[Eclipse Theia] Indirect Prompt Injection via Auto-Loaded Workspace Prompt Template Files in AI Chat

Also known asGHSA-m973-pr9r-hp2w
Published
Jun 18, 2026
Updated
Aug 7, 2026
Affected
6 pkgs
Patched
6 / 6
Exploits
None indexed
Exploitation data as of Aug 7, 2026 · OSV.dev, NVD, FIRST.org (EPSS)

Real-World Exposure

6 pkgs affected

How broadly this vulnerability is actually deployed: weekly install volume shows current usage, a proxy for how much of the ecosystem is exposed.

@theia/ai-chat-uinpm
7Kdownloads / week
@theia/ai-chatnpm
8Kdownloads / week
@theia/ai-claude-codenpm
3Kdownloads / week

Description

In Eclipse Theia versions prior to 1.71.0, files matching the pattern .prompts/*.prompttemplate in a workspace were automatically loaded and could override or extend the AI agent's system prompts. An attacker could craft a malicious repository containing prompt template files that, when the workspace was opened in Theia, replaced the AI's system instructions with attacker-controlled content (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.

Affected Packages

6 total 6 fixed
EcosystemPackageVulnerable rangeFix
📦npm@theia/ai-chat-uiall versions1.71.0
📦npm@theia/ai-chatall versions1.71.0
📦npm@theia/ai-claude-codeall versions1.71.0
📦npm@theia/ai-code-completionall versions1.71.0
📦npm@theia/ai-coreall versions1.71.0
📦npm@theia/ai-editorall versions1.71.0

Detection & mitigation playbook

Open-source dependency
  1. Detect

    Scan your dependency tree (package-lock.json, pnpm-lock.yaml, requirements.txt, go.sum, etc.) for @theia/ai-chat-ui. O3's reachability analysis confirms whether the vulnerable code path is actually invoked in your application, so you act on real exposure instead of every transitive match.

  2. Fix

    Update @theia/ai-chat-ui to 1.71.0 or later, then make sure no transitive (indirect) dependency still pins the vulnerable range — O3 confirms CVE-2026-46580 is resolved across your whole dependency graph.

  3. Workarounds

    If you can't upgrade right away: gate or disable the affected feature, validate untrusted input at the boundary, and avoid passing attacker-controlled data into the vulnerable path. O3's runtime protection blocks exploitation in production as an interim safeguard until the upgrade lands.

  4. How O3 protects you

    O3 pinpoints whether CVE-2026-46580 is reachable in your code and exactly where to fix it, then blocks exploitation in production at runtime until the patched version is deployed.

Tailored to CVE-2026-46580. Runtime protection reduces exposure until a permanent patch is applied and verified — it complements patching, it doesn't replace it.

Frequently Asked Questions

In Eclipse Theia versions prior to 1.71.0, files matching the pattern .prompts/*.prompttemplate in a workspace were automatically loaded and could override or extend the AI agent's system prompts. An attacker could craft a malicious repository containing prompt template files that, when the workspace was opened in Theia, replaced the AI's system instructions with attacker-controlled content (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
O3 Security · Impact-Aware SCA

Is CVE-2026-46580 in your dependencies?

O3 detects CVE-2026-46580 across npm dependencies and uses function-level reachability to confirm whether the vulnerable code path is actually reachable — not just present. No false positives.

CVE-2026-46580: @theia/ai-chat-ui | O3 Security