VulnSea

internlm has 6 CVEs on record. Disclosure cadence is accelerating: 6 in the last 90 days against 0 in the 90 before. The busiest recent month was September 2026 with 5. The median CVSS is 8.7 (high), with 2 rated critical. None have a confirmed exploitation report.

CVEs per month

Last 12 months, by publish date

101112010203040506070809
Exploited share
0% vs 1% corpus
Median CVSS
8.7
Publish → KEV
Last 90 days
6 prev 0

Products

  • lmdeploy 6
6
Total CVEs
2
Critical
0
CISA KEV
0
Exploited

internlm vulnerabilities

CVEs affecting internlm, newest first. Open any entry for full detail, references, and exploit status.

6 CVEsRSS

CVE-2025-66455Critical· 9.8
4d ago

LMDeploy is a toolkit for compressing, deploying, and serving large language models

LMDeploy is a toolkit for compressing, deploying, and serving large language models. Starting in version 0.9.2 and prior to version 0.16.0, LMDeploy's PyTorch DistServe/PD-disaggregation control plane used `recv_pyobj()` to deserialize m…

MidnightInternLM · lmdeployEPSS 0.70%via NVD
CVE-2026-33625High· 8.8
4d ago

LMDeploy is a toolkit for compressing, deploying, and serving large language models

LMDeploy is a toolkit for compressing, deploying, and serving large language models. Versions 012.1 through 0.12.2 contain a code injection vulnerability in `lmdeploy/pytorch/config.py` line 620 that allows an attacker to execute arbitra…

TwilightInternLM · lmdeployEPSS 0.24%via NVD
CVE-2026-92983High· 7.5PoC
5d ago

InternLM LMDeploy through 0.17.0 in DistServe prefill/decode disaggregation mode fails to release scheduler sessions because the proxy uses user-facing session IDs instead of internal scheduler keys

InternLM LMDeploy through 0.17.0 in DistServe prefill/decode disaggregation mode fails to release scheduler sessions because the proxy uses user-facing session IDs instead of internal scheduler keys. Unauthenticated attackers can send co…

MidnightInternLM · lmdeployEPSS 0.37%via NVD
CVE-2026-92971High· 7.5PoC
5d ago

InternLM LMDeploy through 0.17.0 contains a reachable assertion vulnerability in the DistServe decode migration loop that allows unauthenticated attackers to terminate the inference engine

InternLM LMDeploy through 0.17.0 contains a reachable assertion vulnerability in the DistServe decode migration loop that allows unauthenticated attackers to terminate the inference engine. Attackers can submit a migration_request with a…

MidnightInternLM · lmdeployEPSS 0.49%via NVD
CVE-2025-59953Critical· 9.8PoC
6d ago

LMDeploy is a toolkit for compressing, deploying, and serving large language models

LMDeploy is a toolkit for compressing, deploying, and serving large language models. Starting in version 0.9.1 and prior to version 0.10.2, the LMdeploy implements an rpc server (AsyncRPCServer in zmq_rpc.py) for supporting the RPC commu…

AbyssalInternLM · lmdeployEPSS 0.68%via NVD
CVE-2026-63764High· 8.6PoC
2mo ago

LMDeploy through 0.14.0, fixed in commit 03c3130, contains a server-side request forgery (SSRF) vulnerability in the _load_http_url function within the connection.py media handler, where the private-IP guard validates only the original U…

LMDeploy through 0.14.0, fixed in commit 03c3130, contains a server-side request forgery (SSRF) vulnerability in the _load_http_url function within the connection.py media handler, where the private-IP guard validates only the original U…

Midnightinternlm · lmdeployEPSS 0.39%via NVD
internlm vulnerabilities (CVEs) · VulnSea