Skip to main content
VulnerabilityPublished

CVE-2026-105135: InternLM MindSearch · Injection

Affects MindSearchSource GCVE Database

0
Compare
Authoritative record:CVE-2026-105135· Critical 10.0

Public exploit available · CVSS 10.0 Critical.

Data as of 17 Nov 2026, 20:25 UTC

CVSS 4.0 base score
10.0Critical
How severe the flaw is on the 0–10 CVSS scale.
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.
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:P

Exploitation evidence

t = 0 is the CVE’s publication on cve.org

  1. Disclosed: evidence found.

    CVE published 4 Oct 2026

  2. Detectable: no evidence on record.

    No public nuclei template indexed

  3. Weaponized: evidence found.

    CISA SSVC: proof of concept public

  4. Exploited in the wild: no evidence on record.

    Not in CISA KEV and no source reports exploitation

  5. Observed by OffSeq Mirage: no evidence on record.

    No attack traffic recorded by OffSeq Mirage sensors

Timeline

  1. CVE ID reserved

    by VulDB

    , 17 hours before disclosure

  2. CVE published

    on cve.org

    , t = 0

  3. CISA SSVC assessment

    proof of concept public

    , 2 days after disclosure

  4. 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

ProductAffectedFixed in
GitHubinternlm/MindSearchpkg:github/internlm/MindSearchOther threatsAffected
  • =0.1.0
Fixed in–

Check your own hosts for these packages with threat-finder (opens in a new tab), our free open-source scanner.

AI-suggested

Organizations should consider isolating or disabling the affected component until a vendor fix is released. Monitor for any updates from the vendor and apply patches promptly once available.

Description

InternLM MindSearch version 0.1.0 contains a critical code injection vulnerability in the ExecutionAction.run function of its Planner Agent component. This flaw allows remote attackers to manipulate input arguments to execute arbitrary code. The vulnerability has a maximum CVSS score of 10.0, indicating severe impact on confidentiality, integrity, and availability. No patch or remediation is currently available, and the vendor has not responded to inquiries. Although public exploit details exist, there are no reports of active exploitation in the wild.

References

Community reviews

Loading reviews…