# CVE-2026-119613: ash-project ash_ai sensitive information disclosure in error messages

Source: https://junglewise.ai/threats/cve-2026-119613-generation-of-error-message-containing-sensitive-information  
Publisher: Junglewise Threat Intelligence, https://junglewise.ai/threats  
Published: 2026-11-09. Updated: 2026-11-09  
License: CC BY 4.0 with a link back

CVE-2026-119613 · Severity: info · Published 2026-11-09

AshAi, a library for building AI-powered tools, exposes internal error details including module names and data values when tool calls fail. An attacker can craft failing tool calls to read sensitive information that should not be visible, potentially revealing application internals and confidential data values.

Technologies: [Ash-Project Ash Ai](https://junglewise.ai/threats/technologies/ash-ai). Vendors: [Ash-Project](https://junglewise.ai/threats/vendors/ash-project).

## Quick answers

**Is CVE-2026-119613 exploited in the wild?** No. Junglewise Threat Intelligence has no report of CVE-2026-119613 being exploited in the wild.

**How severe is CVE-2026-119613?** Informational severity, published 9 November 2026.

**Which products and versions are affected?** Ash-Project Ash Ai 1.5.0.

**Is there a fix for CVE-2026-119613?** Yes: fixed in ash_ai 1.5.1. Junglewise finds every place you run it, drafts the upgrade and applies it once you approve.

**How is CVE-2026-119613 attacked?** It is attacked over the network, in a software library.

**Am I affected by CVE-2026-119613?** Check whether you run Ash-Project Ash Ai at an affected version. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.

## How to fix

- Fixed in ash_ai 1.5.1

## Technical details

A handler for Ash.Error.Unknown.UnknownError in AshAi.ToToolError returns the full error field without sanitization, which contains Exception.format/2 output or inspect/1 of exceptions. This error text is sent to MCP clients and language models without filtering. Additionally, tool results that fail JSON encoding raise Protocol.UndefinedError with inspected values of complete records. The fix logs these errors with an error ID and returns only the ID to callers, preventing information leakage.

## Affected products

- ash-project ash_ai 1.5.0

## Timeline

- 2026-11-09: disclosed

## References

- [https://repo.hex.pm/](https://repo.hex.pm/)
- [https://github.com/](https://github.com/)

## Related threats

- [ash-project ash_ai information disclosure in error messages](https://junglewise.ai/threats/cve-2026-82580-ash-project-ash-ai-information-disclosure-in-error-messages)
- [Ash AI tool loop infinite loop via prompt injection](https://junglewise.ai/threats/cve-2026-82579-ash-ai-tool-loop-infinite-loop-via-prompt-injection)
- [ash-project ash_ai authorization bypass in identity-configured tools](https://junglewise.ai/threats/cve-2026-82564-ash-project-ash-ai-authorization-bypass-in-identity-configured)
- [ash-project ash_ai sensitive information disclosure in error messages](https://junglewise.ai/threats/cve-2026-75760-ash-project-ash-ai-sensitive-information-disclosure-in-error)
- [ash-project ash_ai origin validation bypass in MCP server](https://junglewise.ai/threats/cve-2026-81315-ash-project-ash-ai-origin-validation-bypass-in-mcp-server)