Internal information disclosure via raw exception serialization
Published Aug 31, 2026 · Updated Aug 31, 2026
Information disclosure in Ash AI 0.6.0 and later before 1.0.0 allows remote authenticated users to read internal exception text via chat. AshAi.ToolLoop and AshAi.Tools serialize Exception.message/1 verbatim into tool-result content without filtering, then append and transmit it through the conversation. Exposure requires an application to expose a tool loop to a chat user who can steer tool arguments into a tool callback or lifecycle hook that raises an exception.
Summary
What happened
Information disclosure in Ash AI 0.6.0 and later before 1.0.0 allows remote authenticated users to read internal exception text via chat. AshAi.ToolLoop and AshAi.Tools serialize Exception.message/1 verbatim into tool-result content without filtering, then append and transmit it through the conversation. Exposure requires an application to expose a tool loop to a chat user who can steer tool arguments into a tool callback or lifecycle hook that raises an exception.
The record
- CVE
- CVE-2026-82580
- Published
- Aug 31, 2026
- Updated
- Aug 31, 2026
- Vendor
- Ash Framework
- Product
- Ash AI
- Classifications
- CWE-209
- Attack vector
- network
- Privileges
- authenticated
Timeline
How it unfolded
- Aug 31, 2026CVE publishedPublication date reported by the CVE source.
- Aug 31, 2026Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=0.6.0 <1.0.0
- Affected versionversion=bc2122f78fca6c11d8ec2b9ac53148ec17476460 <c68dfbdb220426dc015b58379e95bde8e9f0995a
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
- GHSA-5747-6mpw-6m9c proof of conceptproof of concept · demonstrated
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo