AIKIDO-2026-185496
ash_ai is vulnerable to Denial of Service (DoS)
60
Medium Risk
This Affects:
ash_aiTL;DR
AshAi.ToolLoop recurses to process model tool calls, but when every returned tool call is filtered out as invalid or already processed the message list is unchanged and the empty result is not treated as terminal. The loop then re-sends byte-identical requests without advancing the conversation. With the supported :infinity iteration setting the exit check never triggers, causing an uncontrolled loop that exhausts resources. The fix terminates the loop when no unprocessed tool calls remain.
Who does this affect?
You are affected if you are using a version that falls within the vulnerable range and you run tool loops configured with the :infinity iteration setting.
Background info
ash_ai is vulnerable to Denial of Service (DoS) in versions 0.6.0 - 0.8.2.
How to fix this
Upgrade the ash_ai library to the patch version.
Links
GitHub Release
Are You Affected?
Connect your repositories to instantly see whether vulnerable or malicious packages exist in your codebase.
Free. No credit card required.
I consent to receiving marketing communications based on Aikido’s Privacy Policy.
SOC 2Compliant
ISO 27001CompliantISO 42001Compliant
FedRAMPImplementing© All Intel data is openly available and commercially licensed.