Track vulnerabilities like this one.
Sign up free to get alerted when software you use is affected.
9.3
CVE-2026-105135: InternLM MindSearch remote code execution via Planner Agent
CVE-2026-105135 · published 15 days ago
Summary
The Planner Agent in InternLM MindSearch can run crafted input that causes the system to execute any code it wants, and this can be triggered from outside the network. Attackers could take control of the server hosting the software. Apply any available updates, restrict who can send requests to the agent, and validate or sanitize all inputs to the ExecutionAction.run function.
What to do
The CVE record does not list a fixed version. Check the vendor's site or the advisory links below - a fix may already be released.
Affected software
| Vendor | Product | Affected versions |
|---|---|---|
| internlm | mindsearch | 0.1.0 |
Original advisory text
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.
Internet-facing
3 days
Internal
60 days
- Not known to be exploited
- Can be exploited automatically
- Gives an attacker full control
Type
CWE-74Injection
CWE-94Code Injection
Timeline
Published4 Oct 2026
Updated15 Oct 2026
First seen4 Oct 2026
Track software like this
Free during beta