CVE-2026-82580: Information Disclosure

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.

Is your site exposed to CVE-2026-82580?

Run a free security scan — no signup, results in seconds.

Weakness Type (CWE)

CWE-209 CWE-209

References

Other References

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

Frequently Asked Questions

What is CVE-2026-82580? +

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.

How do I check if I'm vulnerable to CVE-2026-82580? +

You can use Secably's free Website Scanner to check your website for known vulnerabilities. For infrastructure scanning, use the Port Scanner to identify exposed services that may be affected. Check the vendor advisories linked above for specific patch and version information.

Related Vulnerabilities

CVE-2026-3259

A Generation of Error Message Containing Sensitive Information vulnerability in the Materialized View Refresh mechanism in Google BigQuery on Google …

CVE-2025-40653

User enumeration vulnerability in M3M Printer Server Web. This issue occurs during user authentication, where a difference in error messages …

CVE-2023-40457

The BGP daemon in Extreme Networks ExtremeXOS (aka EXOS) 30.7.1.1 allows an attacker (who is not on a directly connected …

CVE-2025-9977

Value provided in one of POST parameters sent during the process of logging in to Times Software E-Payroll is not …

CVE-2025-13596

A sensitive information disclosure vulnerability exists in the error handling component of ATISoluciones CIGES Application version 2.15.6 and earlier. When …

CVE-2026-69247

cryptography is a package designed to expose cryptographic primitives and recipes to Python developers. From 44.0.0 until 50.0.0, pkcs7_decrypt_der, pkcs7_decrypt_pem, …

CVE-2026-82580