CVE-2026-105135 InternLM MindSearch Planner Agent graph.py ExecutionAction.run code injection
Remote attackers can execute arbitrary code via manipulated inputs in the MindSearch Planner Agent, requiring immediate mitigation due to public exploit availability.
- Exploited in the wild
- Not known
- Login needed
- Not needed
- Attackable
- Over the internet
- Victim action needed
- Not needed
- Fix
- None listed
What is CVE-2026-105135?
CVE-2026-105135 is a critical code injection vulnerability in InternLM MindSearch, published on 4 Oct 2026. An attacker can exploit it over the internet without logging in, with no action from the victim.
Official description
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.
Which versions are affected by CVE-2026-105135?
How do I fix CVE-2026-105135?
No fix has been published for CVE-2026-105135 yet. Limit exposure of the affected software until one is available.
Upgrade, and never evaluate templates, expressions or code built from user input. More about Code injection.
Is CVE-2026-105135 being exploited?
It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-105135 exists.
Sources
Also known as GHSA-4535-w5r2-pmqp.