CVE-2026-105135: InternLM MindSearch · Code Injection
Affects InternLM MindSearchSource CVE Database V5
Public exploit available · CVSS 10.0 Critical.
Data as of 17 Nov 2026, 20:25 UTC
- EPSS
- 0.7% chance of exploitation in 30 days – higher than 56% of CVEsExploit Prediction Scoring System: the likelihood attackers will use this flaw soon.
- CISA SSVC
- Exploitation
- Proof of concept is public or traded
- Automatable
- Attackers can reliably automate steps 1–4 of the kill chain
- Technical impact
- Total control over the software or total information disclosure
CISA SSVC assessment, 2026-10-06.
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H/E:PExploitation evidence
t = 0 is the CVE’s publication on cve.org
Disclosed: evidence found.
CVE published 4 Oct 2026
Detectable: no evidence on record.
No public nuclei template indexed
Weaponized: evidence found.
CISA SSVC: proof of concept public
Exploited in the wildExploited: no evidence on record.
Not in CISA KEV and no source reports exploitation
Observed by OffSeq MirageSeen by Mirage: no evidence on record.
No attack traffic recorded by OffSeq Mirage sensors
Timeline
CVE ID reserved
by VulDB
, 17 hours before disclosure
CVE published
on cve.org
, t = 0
CISA SSVC assessment
proof of concept public
, 2 days after disclosure
In Threat Radar
record ingested
, 22 days after disclosure
A missing step is not evidence of safety. Sources: cve.org (opens in a new tab), CISA SSVC, the Metasploit, Exploit-DB and nuclei-templates index as of 17 Nov 2026.
What to do
Affected software
| Product | Affected | Fixed in |
|---|---|---|
| InternLMMindSearch | Affected
| Fixed in– |
CPE configurations (1)
cpe:2.3:a:internlm:mindsearch:*:*:*:*:*:*:*:*
AI-suggested
Users should consider disabling or isolating the affected component (ExecutionAction.run in MindSearch 0.1.0) until a fix is available. Monitor official vendor channels for updates. Employ network-level protections to restrict access to the vulnerable service to trusted sources only.
Description
CVE-2026-105135 is a critical code injection vulnerability in InternLM MindSearch version 0.1.0. It affects the ExecutionAction.run function in the mindsearch/agent/graph.py file within the Planner Agent component. The vulnerability allows remote attackers to manipulate the inputs argument to inject and execute arbitrary code. The exploit has been publicly disclosed, and the vendor has not responded to the disclosure.