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.
Published: 2026-08-31
Score: 5.3 Medium
EPSS: < 1% Very Low
KEV: No
Impact: n/a
Action: n/a
AI Analysis

Impact

The vulnerability in ash_ai allows error messages that originate inside tool execution or lifecycle hooks to be serialized without transformation and appended to the conversation stream. Because the exception text is sent back to the language model and relayed to the user, any internal details such as database constraint violations, adapter errors, or query fragments can be disclosed. The flaw falls under CWE‑209, a weakness in preventing information disclosure through unfiltered messages.

Affected Systems

The issue affects the ash‑project ash_ai product for all releases starting from 0.6.0 up to, but not including, 1.0.0.

Risk and Exploitability

The CVSS score of 5.3 indicates moderate severity, and the EPSS score is currently unavailable while the vulnerability is not listed in CISA KEV, suggesting limited public exploitation. The likely attack vector requires a user able to supply crafted tool arguments that trigger a raising path; the disclosure is confined to the conversation output with no impact on system integrity or availability.

Generated by OpenCVE AI on August 31, 2026 at 02:21 UTC.

Remediation

No vendor fix or workaround currently provided.

OpenCVE Recommended Actions

  • Upgrade ash_ai to version 1.0.0 or later, which routes tool errors through the safe formatter and prevents raw exception leakage.
  • If an upgrade cannot occur immediately, modify the tool error handling configuration to filter exception messages before they reach the conversation stream.
  • Validate and sanitize tool invocation parameters to avoid triggering internal exception paths that expose sensitive details.

Generated by OpenCVE AI on August 31, 2026 at 02:21 UTC.

Tracking

Sign in to view the affected projects.

Advisories

No advisories yet.

History

Mon, 31 Aug 2026 01:45:00 +0000

Type Values Removed Values Added
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.
Title AshAi echoes raw tool exception messages into the conversation, disclosing internal details
First Time appeared Ash-project
Ash-project ash Ai
Weaknesses CWE-209
CPEs cpe:2.3:a:ash-project:ash_ai:*:*:*:*:*:*:*:*
Vendors & Products Ash-project
Ash-project ash Ai
References
Metrics cvssV4_0

{'score': 5.3, 'vector': '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'}

Subscriptions

Ash-project Ash Ai
cve-icon MITRE

Status: PUBLISHED

Assigner: EEF

Published:

Updated: 2026-08-31T01:09:00.192Z

Reserved: 2026-08-30T15:00:01.232Z

Link: CVE-2026-82580

cve-icon Vulnrichment

No data.

cve-icon NVD

Status : Received

Published: 2026-08-31T02:17:02.440

Modified: 2026-08-31T02:17:02.440

Link: CVE-2026-82580

cve-icon Redhat

No data.

cve-icon OpenCVE Enrichment

Updated: 2026-08-31T06:30:05Z

Weaknesses
  • CWE-209

    Generation of Error Message Containing Sensitive Information