CVE-2026-82579: CWE-835 Loop with Unreachable Exit Condition ('Infinite Loop') in ash-project ash_ai
Description
CVE-2026-82579 is an infinite loop vulnerability in the ash_ai tool of the ash-project. The vulnerability occurs when the tool loop processes model responses that result in an empty list after filtering, causing the loop to recurse indefinitely without advancing the conversation. This can lead to unbounded repeated model requests, potentially hanging the tool. The issue affects versions from 0.6.0 up to but not including 1.0.0.
CVSS v4.0
Score 6.0medium
Affected software
ash-project
ash_ai
ash-project
ash_ai
cpe:2.3:a:ash-project:ash_ai:*:*:*:*:*:*:*:*Run on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.
Weaknesses
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
The vulnerability arises in the AshAi.ToolLoop component, which classifies model responses and filters tool calls. If the filtered list of tool calls is empty—due to missing valid names or reuse of tool_call_id already present in history—the loop appends nothing and recurses with the same message list. This causes an infinite loop under the max_iterations setting of :infinity or exhausts the iteration budget otherwise. Prompt injection can cause the model to re-emit spent tool_call_ids, triggering this condition. The fix involves treating an empty post-filter list as a terminal condition to break the loop.
Potential Impact
An attacker who can influence the model's output can cause the ash_ai tool to hang by triggering an infinite loop, resulting in unbounded repeated requests. This can degrade availability and potentially lead to denial of service conditions for the tool. No direct code execution or data breach impact is described.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Until a fix is available, users should monitor for unusual looping behavior and avoid configurations that allow unbounded max_iterations. Mitigation should focus on preventing prompt injection that causes reuse of spent tool_call_ids.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- EEF
- Date Reserved
- 2026-08-30T20:00:01.852Z
- Cvss Version
- 4.0
- State
- PUBLISHED
Threat ID: 6a94db21acd9273b495a1eb3
Added to database: 08/31/2026, 01:38:41 UTC
Last enriched: 09/07/2026, 15:40:54 UTC
Last updated: 10/13/2026, 18:48:24 UTC
Views: 89
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
Need more coverage?
Upgrade to Pro Console for AI refresh and higher limits.
For incident response and remediation, OffSeq services can help resolve threats faster.
Latest Threats
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.