CVE-2026-82580
AshAi tool exceptions could leak internal error details
ash-project · ash_ai
First documented disclosure · Review checkpoint
Summary
Raised tool errors could be exposed through the model conversation and stream.
Severity and exploitation evidence
Medium · 5.3/10 · CVSS 4.0. Severity source.
Exploitation not established: Malicious exploitation is not established by the reviewed originals. Public demonstrations and catalog absence do not establish exploitation status.
Technical severity is not a measure of observed attacks or of risk to your deployment. Attempts, demonstrations, and successful compromise retain the qualifications in the source.
How the weakness works
ToolLoop and Tools serialized raw exception messages without the ordinary safe formatter.
Conditions required
A chat user can steer a tool callback or lifecycle hook into an exception path.
Potential impact
Database constraints, query fragments and policy or validation internals can reach the model and user.
Affected versions and configurations
ash_ai: 0.6.0 through versions before 1.0.0.
Fix and mitigation status
1.0.0.
Practical next steps
Apply the issue-specific correction: 1.0.0.
Operating lesson
Apply one safe error formatter to every tool failure path.
Evidence and limits
Earliest reviewed public evidence 2026-08-30; CVE publication 2026-08-31. CVSS 4.0 5.3 is attributed to EEF in the CNA record.
Sources
- EEF CVE authority record
Primary source ·
- Original maintainer advisory or correction
Primary source ·
- Original maintainer advisory or correction
Primary source ·