Service hang via empty post-filter tool calls
Published Aug 31, 2026 · Updated Aug 31, 2026
Uncontrolled looping in Ash AI 0.6.0 through 0.8.2 allows remote authenticated users to hang tool-loop consumers via model output. The AshAi.ToolLoop run and stream paths filter invalid or previously processed tool calls to an empty list, then recurse without changing the message history and resend the identical paid model request. Exploitation requires influence over content ingested by the model and a replayed tool-call ID; the infinity setting hangs indefinitely, while finite limits consume the configured request budget.
Summary
What happened
Uncontrolled looping in Ash AI 0.6.0 through 0.8.2 allows remote authenticated users to hang tool-loop consumers via model output. The AshAi.ToolLoop run and stream paths filter invalid or previously processed tool calls to an empty list, then recurse without changing the message history and resend the identical paid model request. Exploitation requires influence over content ingested by the model and a replayed tool-call ID; the infinity setting hangs indefinitely, while finite limits consume the configured request budget.
The record
- CVE
- CVE-2026-82579
- Published
- Aug 31, 2026
- Updated
- Aug 31, 2026
- Vendor
- Ash Framework
- Product
- Ash AI
- Classifications
- CWE-835, T1499.004
- 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 <53325fdab90afab628c6a53232ef2a9001580bd9
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
- Maintainer ToolLoop no-progress loop 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