Vendor
Internlm vulnerabilities
Updated . Rebuilt every hour.
Junglewise Threat Intelligence has tracked 13 vulnerabilities in Internlm: 1 in the last 7 days and 8 in the last 90 days, 4 of them critical and 0 exploited in the wild. The most recent, CVE-2026-123818, was published on 9 November 2026. 1 vulnerability in the last four weeks, down 80% on the four before (5). 1 critical against 1. 1 technology has a page of its own.
- Last 7 days
- 1
- Last 90 days
- 8
- Critical, all time
- 4
- Exploited in the wild
- 0
About Internlm
Chinese open-source artificial intelligence research organization.
Internlm technologies
Latest Internlm vulnerabilities
- CVE-2026-123818: LMDeploy URL validation bypass via backslash interpretationhighCVSS 7.5EPSS 0.3%
- CVE-2026-119706: InternLM LMDeploy unauthenticated remote code execution in /update_weightscriticalCVSS 9.8
- CVE-2026-33625: LMDeploy arbitrary code execution via eval() of untrusted quant_dtypehighCVSS 8.8EPSS 0.4%
- CVE-2025-66455: LMDeploy remote code execution via pickle deserialization in DistServecriticalCVSS 9.8EPSS 0.7%
- LMDeploy SSRF bypass in URL validationlowCVSS 3.1
- CVE-2026-92983: InternLM LMDeploy memory leak in DistServe disaggregation modehighCVSS 7.5EPSS 0.7%
- CVE-2026-92971: InternLM LMDeploy assertion failure in DistServe decode migrationhighCVSS 7.5EPSS 0.7%
- CVE-2026-76850: LMDeploy unsafe pickle deserialization in disaggregated servingcriticalCVSS 9.8EPSS 1.4%
- CVE-2026-63764: InternLM lmdeploy SSRF via HTTP redirect bypass in API servercriticalCVSS 9.3
- CVE-2026-46517: InternLM LMDeploy remote code execution via hardcoded trust_remote_codehighCVSS 7.8EPSS 0.4%
- CVE-2026-46432: InternLM LMDeploy arbitrary code execution via hardcoded trust_remote_codehighCVSS 7.8EPSS 0.2%
- CVE-2026-33626: LMDeploy server-side request forgery in vision-language image loadinghighCVSS 7.5EPSS 45.3%
- CVE-2025-67729: PYSEC-2026-1578 - lmdeploy vulnerable to Arbitrary Code Execution via Insecure Deserialization in torch.load()highCVSS 8.8EPSS 0.6%
Most severe Internlm vulnerabilities
Exploited in the wild first, then by severity and CVSS score.
- CVE-2026-76850: LMDeploy unsafe pickle deserialization in disaggregated servingcriticalCVSS 9.8EPSS 1.4%
- CVE-2025-66455: LMDeploy remote code execution via pickle deserialization in DistServecriticalCVSS 9.8EPSS 0.7%
- CVE-2026-119706: InternLM LMDeploy unauthenticated remote code execution in /update_weightscriticalCVSS 9.8
- CVE-2026-63764: InternLM lmdeploy SSRF via HTTP redirect bypass in API servercriticalCVSS 9.3
- CVE-2025-67729: PYSEC-2026-1578 - lmdeploy vulnerable to Arbitrary Code Execution via Insecure Deserialization in torch.load()highCVSS 8.8EPSS 0.6%
- CVE-2026-33625: LMDeploy arbitrary code execution via eval() of untrusted quant_dtypehighCVSS 8.8EPSS 0.4%
- CVE-2026-46517: InternLM LMDeploy remote code execution via hardcoded trust_remote_codehighCVSS 7.8EPSS 0.4%
- CVE-2026-46432: InternLM LMDeploy arbitrary code execution via hardcoded trust_remote_codehighCVSS 7.8EPSS 0.2%
- CVE-2026-33626: LMDeploy server-side request forgery in vision-language image loadinghighCVSS 7.5EPSS 45.3%
- CVE-2026-92971: InternLM LMDeploy assertion failure in DistServe decode migrationhighCVSS 7.5EPSS 0.7%
Vulnerabilities per week
1 vulnerability in the last four weeks, down 80% on the four before (5). 1 critical against 1. The last 13 weeks, by the week each vulnerability was published.
| Week of | Bar | Vulns | Critical |
|---|---|---|---|
| 17 Aug 2026 | 1 | 1 | |
| 24 Aug 2026 | 0 | 0 | |
| 31 Aug 2026 | 0 | 0 | |
| 7 Sep 2026 | 0 | 0 | |
| 14 Sep 2026 | 5 | 1 | |
| 21 Sep 2026 | 0 | 0 | |
| 28 Sep 2026 | 0 | 0 | |
| 5 Oct 2026 | 0 | 0 | |
| 12 Oct 2026 | 0 | 0 | |
| 19 Oct 2026 | 0 | 0 | |
| 26 Oct 2026 | 1 | 1 | |
| 2 Nov 2026 | 0 | 0 | |
| 9 Nov 2026 | 1 | 0 |
Embed a badge
A live badge for a README, a status page or an internal wiki: how many Internlm vulnerabilities were published in the last 7 days and how many of them are critical, refreshed hourly.
[](https://junglewise.ai/threats/vendors/internlm)<a href="https://junglewise.ai/threats/vendors/internlm"><img src="https://junglewise.ai/threats/vendors/internlm/badge.svg" alt="Internlm vulnerabilities" /></a>How this is built
Junglewise Threat Intelligence collects vulnerabilities from NVD, GitHub Security Advisories, OSV, the CISA Known Exploited Vulnerabilities catalog, FIRST EPSS and vendor advisories, and matches each one to the technologies and vendors it affects. Dates are the date a vulnerability was published, in UTC.
The pages are rebuilt from the database every hour. Frozen weekly and monthly reports never change once published, so they can be cited.
Use this data
The same data is at https://junglewise.ai/threats/vendors/internlm.json, and this page as text at https://junglewise.ai/threats/vendors/internlm.md, for scripts and language models. It is free to reuse under CC BY 4.0 with a link back to this page.
Cite as: Junglewise Threat Intelligence, "Internlm vulnerabilities", https://junglewise.ai/threats/vendors/internlm, 13 November 2026.