CVE-2026-105135: InternLM MindSearch Planner Agent graph.py ExecutionAction.run code injection
A vulnerability has been found in InternLM MindSearch 0.1.0. This issue affects the function ExecutionAction.run of the file mindsearch/agent/graph.py of the component Planner Agent. The manipulation of the argument inputs leads to code injection. The attack can be initiated remotely. The exploit has been disclosed to the public and may be used. The vendor was contacted early about this disclosure but did not respond in any way.
Affected Software
Event History
Frequently Asked Questions
What access does an attacker need to exploit this issue?
The issue is remotely exploitable and requires no privileges or user interaction. An attacker can trigger code injection by manipulating the inputs argument handled by ExecutionAction.run in the Planner Agent.
Which deployments are affected?
The affected product identified in the available information is InternLM MindSearch 0.1.0, specifically the Planner Agent component in mindsearch/agent/graph.py. The vulnerable function is ExecutionAction.run.
Is public exploit information available?
Yes. The exploit has been publicly disclosed and may be used, increasing the likelihood of exploitation.
What are the potential consequences of successful exploitation?
Successful exploitation can result in code injection with high impacts to confidentiality, integrity, and availability. The supplied severity data also indicates the impact can extend beyond the vulnerable component's security scope.