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.
Default status is the baseline for the product, each version can override it (e.g. patched versions marked unaffected).
| Vendor | Product | Default status | Versions | ||||||
|---|---|---|---|---|---|---|---|---|---|
| ash-project | ash_ai | unaffected |
|
||||||
| ash-project | ash_ai | unaffected |
|
No data.
No data.
OpenCVE Enrichment is a feature of OpenCVE that uses AI to automatically link vendors and products to CVEs. Learn more on GitHub.
No data.
No advisories yet.
Solution
No solution given by the vendor.
Workaround
No workaround given by the vendor.
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
|
Projects
Sign in to view the affected projects.
MITRE
Status: PUBLISHED
Assigner: EEF
Published:
Updated: 2026-08-31T01:09:00.192Z
Reserved: 2026-08-30T15:00:01.232Z
Link: CVE-2026-82580
Vulnrichment
No data.
NVD
Status : Received
Published: 2026-08-31T02:17:02.440
Modified: 2026-08-31T02:17:02.440
Link: CVE-2026-82580
Redhat
No data.
OpenCVE Enrichment
Updated: 2026-08-31T02:30:18Z