CVE-2026-119613 json
AshAi sends unrecognized tool errors verbatim to MCP clients and the model, disclosing internal details
published 4d ago modified 2d ago also EEF-CVE-2026-119613 , EUVD-2026-120053 , GHSA-vhmw-fwrr-r6c6
- cvss
- 5.3
- version 4.0, CNA
- cisa kev
- Not listed
- not in CISA's catalog
- epss
- 0.3%
- EPSS 0.3% chance of exploitation in 30 days, percentile 19%
- public exploits
- 0
- none known
Summary
Generation of Error Message Containing Sensitive Information vulnerability in ash-project ash_ai allows a caller of an AshAi tool to read internal error details, including module names and data values, by making a tool call fail.
AshAi.ToToolError gained an implementation for Ash.Error.Unknown.UnknownError that returns the error's error field as is, and AshAi.Tool.Errors.format/1 sends that text to MCP clients (tool calls and resource reads in AshAi.Mcp.Server) and to the model in AshAi.ToolLoop. Ash stores the full Exception.format/2 output of a raised exception, or inspect/1 of a bare {:error, term} return, in that field. A tool result that cannot be JSON-encoded raises a Protocol.UndefinedError whose text includes the inspected value, which can be a whole record with fields the tool never returns. None of these errors were logged. The fix logs them under an error id and returns only that id to the caller.
This issue affects ash_ai: from 1.5.0 before 1.5.1.
Patch / fix
- hex ash_ai 1.5.1
- ash-project ash_ai 1.5.1
Is CVE-2026-119613 in your dependencies? Fencer shows which of your repositories are affected as soon as an advisory lands, and opens the fix as a pull request.
Check with FencerExploit prediction
0.27% chance of exploitation in the next 30 days, higher than 19% of all scored CVEs (FIRST EPSS, 2026-11-11).
CVSS scores
| assigned by | version | score | vector |
|---|---|---|---|
| CNA | 4.0 | 5.3 | CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:L/VI:N/VA:N/SC:N/SI:N/SA:N |
| CNA | 4.0 | 5.3 | CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:L/VI:N/VA:N/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X |
Affected packages
| ecosystem | package | affected | fixed in |
|---|---|---|---|
| hex | ash_ai | >=1.5.0, <1.5.1 |
1.5.1 |
Affected products
- ash-project ash_ai
Classification
- Weakness
-
- CWE-209 Generation of Error Message Containing Sensitive Information
References
-
github.com
/ash-project/ash_ai/commit/fbad04e9620ef70603f4e67e03f15092f58578f6
related, web
-
github.com
/ash-project/ash_ai/commit/af7987769d78ed070c8a9f6e6ee542d91744eae6
patch
-
github.com
/ash-project/ash_ai/security/advisories/GHSA-vhmw-fwrr-r6c6
vendor-advisory, related, advisory
-
cna.erlef.org
/cves/CVE-2026-119613.html
related, web
-
osv.dev
/vulnerability/EEF-CVE-2026-119613
related
-
hex.pm
/packages/ash_ai
package
Sources
- CVE List CVE-2026-119613
- NVD CVE-2026-119613
- OSV EEF-CVE-2026-119613
- Maintainer advisory GHSA-vhmw-fwrr-r6c6
Fencer Intel keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.
The maintainers of ash-project/ash_ai published their own advisory on GitHub. Reviewed sources take precedence over it.