CVE-2026-134006: Moonshot AI Kimi Code Plan Mode Permission Guard planService.ts guardToolExecution improper authorization
A weakness has been identified in Moonshot AI Kimi Code up to 2.7.2. This vulnerability affects the function guardToolExecution of the file packages/agent-core-v2/src/features/plan/planService.ts of the component Plan Mode Permission Guard. Executing a manipulation can lead to improper authorization. The attack requires local access. The exploit has been made available to the public and could be used for attacks. The vendor was contacted early about this disclosure but did not respond in any way.
Affected Software
Event History
Frequently Asked Questions
Who is realistically exposed to this issue?
Systems running Moonshot AI Kimi Code version 2.7.2 or earlier are in scope. Exploitation requires local access and low privileges, so it is primarily relevant where untrusted or insufficiently trusted users can access the local environment.
What does an attacker need to exploit it?
An attacker needs local access and low privileges. No user interaction is required, and a public exploit is available.
What component should be reviewed during triage?
The affected code is the Plan Mode Permission Guard, specifically the guardToolExecution function in packages/agent-core-v2/src/features/plan/planService.ts. The reported impact is improper authorization.