# CVE-2026-82580

## Summary

- **CVE ID:** CVE-2026-82580
- **Severity:** MEDIUM
- **CVSS Score:** 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)
- **CWE:** CWE-209
- **Published:** Aug 31, 2026
- **Last Modified:** Aug 31, 2026

## Description

Generation of Error Message Containing Sensitive Information vulnerability in ash-project ash_ai discloses internal error text to chat users.

In AshAi.ToolLoop and AshAi.Tools, an exception raised while executing a tool was serialized verbatim with Exception.message/1 into the tool-result content. That content is appended to the conversation, emitted as a {:tool_result, ...} stream event, and sent back to the model, which typically relays it to the user. No filtering happened first, so anything raised inside a tool callback or lifecycle hook (database constraint messages, adapter errors, query fragments, policy or validation internals) was echoed as-is. A chat user who can steer tool arguments into a raising code path receives the raw internal text. The fix routes raised tool errors through the same safe formatter used for other tool errors.

This issue affects ash_ai: from 0.6.0 before 1.0.0.

## Affected Products

- ash-project — ash_ai (0.6.0)
- ash-project — ash_ai (bc2122f78fca6c11d8ec2b9ac53148ec17476460)

## References

- [CNA](https://github.com/ash-project/ash_ai/security/advisories/GHSA-5747-6mpw-6m9c)
- [CNA](https://cna.erlef.org/cves/CVE-2026-82580.html)
- [CNA](https://osv.dev/vulnerability/EEF-CVE-2026-82580)
- [CNA](https://github.com/ash-project/ash_ai/commit/c68dfbdb220426dc015b58379e95bde8e9f0995a)

## Exploitation Prediction (EPSS)

- **EPSS Score:** 0.27%
- **EPSS Percentile:** 18.8

---
_Exported from OnDuty AI Vulnerability Intelligence on 2026-09-11._