Intel

AIKIDO-2026-791500

ash_ai is vulnerable to Generation of Error Message Containing Sensitive Information

CVE-2026-119613Published 4 days ago
November 16, 2026

53

CVE Score

Medium

Generation of Error Message Containing Sensitive Information

Are you affected? Scan for Free

TL;DR

When a tool action raised, returned a bare error, or produced a result that could not be JSON-encoded, AshAi 1.5.0 sent raw error text to the caller, exposing internal details and potentially data values. An MCP client or the model in AshAi.ToolLoop could receive those details when calling the affected tool. The fix returned an error identifier instead of the raw details.

How do I fix this?

Upgrade the ash_ai package to 1.5.1 or later.

Who does this affect?

You are affected if you are using a version that falls within the vulnerable range of ash_ai and expose tools through AshAi.Mcp.Router or AshAi.ToolLoop.

Package

Versions

1.5.0 - 1.5.0

Fixed in 1.5.1

Background info

ash_ai is vulnerable to Generation of Error Message Containing Sensitive Information in versions 1.5.0 - 1.5.0.

Get secure today,
quickly and for free.

Secure your code, cloud, and runtime in one central system. Connect a repo to discover what the reasoning agents find in your codebase.

No credit card required | Scan results in 32 seconds.

Trusted by 150k+ orgs
  • Revolut
  • n8n
  • Lovable
  • Deel
  • Prove
  • Omnea