Answer in brief
CVE-2026-82580 records a Medium severity (CVSS 5.3) vulnerability in AshAi echoes raw tool exception messages into the conversation, disclosing internal details. The current sources do not mark it as known exploited. The current feed maps ash-project/ash_ai (generic), ash-project/ash_ai (generic), ash-project/ash-project/ash_ai (generic). Check affected ranges and fixed versions before updating.
Analysis pending evidence review
HOL Guard separates source facts from reviewed analysis. See the methodology.
CVSS is 5.3. The current sources do not mark it as known exploited. Treat this as a source-backed prioritization signal, not a statement about your environment.
Analysis status
Analysis pending evidence review
Factual feed record only; HOL analysis is not approved for indexing. Read the methodology.
The current feed maps ash-project/ash_ai (generic), ash-project/ash_ai (generic), ash-project/ash-project/ash_ai (generic). Check affected ranges and fixed versions before updating.
| Package | Affected range | Fixed version |
|---|---|---|
| ash-project/ash_aigeneric | >=bc2122f78fca6c11d8ec2b9ac53148ec17476460 <c68dfbdb220426dc015b58379e95bde8e9f0995a | c68dfbdb220426dc015b58379e95bde8e9f0995a |
| ash-project/ash_aigeneric | >=0.6.0 <1.0.0 | 1.0.0 |
| ash-project/ash-project/ash_aigeneric | >=bc2122f78fca6c11d8ec2b9ac53148ec17476460 <c68dfbdb220426dc015b58379e95bde8e9f0995a | c68dfbdb220426dc015b58379e95bde8e9f0995a |
Published upstream
Aug 31, 2026
Evidence: source:cvelist:source_dates:source-dates:recordSource modified
Sep 1, 2026
Evidence: source:cvelist:source_dates:source-dates:recordFirst seen by HOL
Aug 31, 2026
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.
Quoted source text, attributed separately from HOL analysis.