# lmdeploy (PyPI) vulnerabilities Source: https://junglewise.ai/threats/technologies/lmdeploy Publisher: Junglewise Threat Intelligence, https://junglewise.ai/threats Updated: 13 November 2026, 03:07 UTC. Rebuilt every hour. Data: https://junglewise.ai/threats/technologies/lmdeploy.json License: CC BY 4.0 with a link back Junglewise Threat Intelligence has tracked 14 vulnerabilities in lmdeploy (PyPI): 0 in the last 7 days and 7 in the last 90 days, 4 of them critical and 0 exploited in the wild. The most recent, CVE-2026-33625, was published on 18 September 2026. Nothing in the last four weeks, down from 6 vulnerabilities in the four before. 0 critical against 2. ## Counts - Last 7 days: 0 - Last 30 days: 0 - Last 90 days: 7 - All time: 14 (4 critical, 0 exploited in the wild) ## About lmdeploy (PyPI) Large model deployment toolkit for efficient inference and serving. ## Latest lmdeploy (PyPI) vulnerabilities - [CVE-2026-33625: LMDeploy arbitrary code execution via eval() of untrusted quant_dtype](https://junglewise.ai/threats/cve-2026-33625-lmdeploy-arbitrary-code-execution-via-eval-of-untrusted-quant) (high, CVSS 8.8, published 18 Sep 2026) - [CVE-2025-66455: LMDeploy remote code execution via pickle deserialization in DistServe](https://junglewise.ai/threats/cve-2025-66455-lmdeploy-remote-code-execution-via-pickle-deserialization-in) (critical, CVSS 9.8, published 18 Sep 2026) - [LMDeploy SSRF bypass in URL validation](https://junglewise.ai/threats/lmdeploy-ssrf-bypass-in-url-validation-c4a40a8d) (low, CVSS 3.1, published 18 Sep 2026) - [CVE-2026-92983: InternLM LMDeploy memory leak in DistServe disaggregation mode](https://junglewise.ai/threats/cve-2026-92983-internlm-lmdeploy-memory-leak-in-distserve-disaggregation-mode) (high, CVSS 7.5, published 17 Sep 2026) - [CVE-2026-92971: InternLM LMDeploy assertion failure in DistServe decode migration](https://junglewise.ai/threats/cve-2026-92971-internlm-lmdeploy-assertion-failure-in-distserve-decode-migration) (high, CVSS 7.5, published 17 Sep 2026) - [CVE-2025-59953: LMdeploy remote code execution via pickle deserialization in zmq_rpc](https://junglewise.ai/threats/cve-2025-59953-lmdeploy-remote-code-execution-via-pickle-deserialization-in-zmq) (critical, CVSS 9.8, published 16 Sep 2026) - [CVE-2026-76850: LMDeploy unsafe pickle deserialization in disaggregated serving](https://junglewise.ai/threats/cve-2026-76850-lmdeploy-unsafe-pickle-deserialization-in-disaggregated-serving) (critical, CVSS 9.8, published 19 Aug 2026) - [CVE-2026-63764: InternLM lmdeploy SSRF via HTTP redirect bypass in API server](https://junglewise.ai/threats/cve-2026-63764-internlm-lmdeploy-ssrf-via-http-redirect-bypass-in-api-server) (critical, CVSS 9.3, published 21 Jul 2026) - [CVE-2025-3163: PYSEC-2026-1579 - InternLM LMDeploy code injection vulnerability](https://junglewise.ai/threats/cve-2025-3163-internlm-lmdeploy-code-injection-vulnerability) (low, CVSS 3.1, published 7 Jul 2026) - [CVE-2025-3162: PYSEC-2026-1577 - LMDeploy Improper Input Validation Vulnerability](https://junglewise.ai/threats/cve-2025-3162-lmdeploy-improper-input-validation-vulnerability) (low, CVSS 3.1, published 7 Jul 2026) - [CVE-2026-46517: InternLM LMDeploy remote code execution via hardcoded trust_remote_code](https://junglewise.ai/threats/cve-2026-46517-internlm-lmdeploy-remote-code-execution-via-hardcoded-trust) (high, CVSS 7.8, published 10 Jun 2026) - [CVE-2026-46432: InternLM LMDeploy arbitrary code execution via hardcoded trust_remote_code](https://junglewise.ai/threats/cve-2026-46432-internlm-lmdeploy-arbitrary-code-execution-via-hardcoded-trust) (high, CVSS 7.8, published 10 Jun 2026) - [CVE-2026-33626: LMDeploy server-side request forgery in vision-language image loading](https://junglewise.ai/threats/cve-2026-33626-lmdeploy-has-server-side-request-forgery-ssrf-via-vision-language) (high, CVSS 7.5, published 20 Apr 2026) - [CVE-2025-67729: PYSEC-2026-1578 - lmdeploy vulnerable to Arbitrary Code Execution via Insecure Deserialization in torch.load()](https://junglewise.ai/threats/cve-2025-67729-lmdeploy-vulnerable-to-arbitrary-code-execution-via-insecure) (high, CVSS 8.8, published 26 Dec 2025) ## Most severe lmdeploy (PyPI) vulnerabilities - [CVE-2026-76850: LMDeploy unsafe pickle deserialization in disaggregated serving](https://junglewise.ai/threats/cve-2026-76850-lmdeploy-unsafe-pickle-deserialization-in-disaggregated-serving) (critical, CVSS 9.8, published 19 Aug 2026) - [CVE-2025-59953: LMdeploy remote code execution via pickle deserialization in zmq_rpc](https://junglewise.ai/threats/cve-2025-59953-lmdeploy-remote-code-execution-via-pickle-deserialization-in-zmq) (critical, CVSS 9.8, published 16 Sep 2026) - [CVE-2025-66455: LMDeploy remote code execution via pickle deserialization in DistServe](https://junglewise.ai/threats/cve-2025-66455-lmdeploy-remote-code-execution-via-pickle-deserialization-in) (critical, CVSS 9.8, published 18 Sep 2026) - [CVE-2026-63764: InternLM lmdeploy SSRF via HTTP redirect bypass in API server](https://junglewise.ai/threats/cve-2026-63764-internlm-lmdeploy-ssrf-via-http-redirect-bypass-in-api-server) (critical, CVSS 9.3, published 21 Jul 2026) - [CVE-2025-67729: PYSEC-2026-1578 - lmdeploy vulnerable to Arbitrary Code Execution via Insecure Deserialization in torch.load()](https://junglewise.ai/threats/cve-2025-67729-lmdeploy-vulnerable-to-arbitrary-code-execution-via-insecure) (high, CVSS 8.8, published 26 Dec 2025) - [CVE-2026-33625: LMDeploy arbitrary code execution via eval() of untrusted quant_dtype](https://junglewise.ai/threats/cve-2026-33625-lmdeploy-arbitrary-code-execution-via-eval-of-untrusted-quant) (high, CVSS 8.8, published 18 Sep 2026) - [CVE-2026-46517: InternLM LMDeploy remote code execution via hardcoded trust_remote_code](https://junglewise.ai/threats/cve-2026-46517-internlm-lmdeploy-remote-code-execution-via-hardcoded-trust) (high, CVSS 7.8, published 10 Jun 2026) - [CVE-2026-46432: InternLM LMDeploy arbitrary code execution via hardcoded trust_remote_code](https://junglewise.ai/threats/cve-2026-46432-internlm-lmdeploy-arbitrary-code-execution-via-hardcoded-trust) (high, CVSS 7.8, published 10 Jun 2026) - [CVE-2026-33626: LMDeploy server-side request forgery in vision-language image loading](https://junglewise.ai/threats/cve-2026-33626-lmdeploy-has-server-side-request-forgery-ssrf-via-vision-language) (high, CVSS 7.5, published 20 Apr 2026) - [CVE-2026-92971: InternLM LMDeploy assertion failure in DistServe decode migration](https://junglewise.ai/threats/cve-2026-92971-internlm-lmdeploy-assertion-failure-in-distserve-decode-migration) (high, CVSS 7.5, published 17 Sep 2026) ## Vulnerabilities per week Nothing in the last four weeks, down from 6 vulnerabilities in the four before. 0 critical against 2. | Week of | Vulns | Critical | Exploited | | --- | --- | --- | --- | | 17 Aug 2026 | 1 | 1 | 0 | | 24 Aug 2026 | 0 | 0 | 0 | | 31 Aug 2026 | 0 | 0 | 0 | | 7 Sep 2026 | 0 | 0 | 0 | | 14 Sep 2026 | 6 | 2 | 0 | | 21 Sep 2026 | 0 | 0 | 0 | | 28 Sep 2026 | 0 | 0 | 0 | | 5 Oct 2026 | 0 | 0 | 0 | | 12 Oct 2026 | 0 | 0 | 0 | | 19 Oct 2026 | 0 | 0 | 0 | | 26 Oct 2026 | 0 | 0 | 0 | | 2 Nov 2026 | 0 | 0 | 0 | | 9 Nov 2026 | 0 | 0 | 0 | ## Other PyPI technologies - [tensorflow (PyPI)](https://junglewise.ai/threats/technologies/pypi-tensorflow): 435 vulnerabilities - [tensorflow-cpu (PyPI)](https://junglewise.ai/threats/technologies/tensorflow-cpu): 430 vulnerabilities - [tensorflow-gpu (PyPI)](https://junglewise.ai/threats/technologies/tensorflow-gpu): 427 vulnerabilities - [open-webui (PyPI)](https://junglewise.ai/threats/technologies/open-webui): 177 vulnerabilities - [Django (PyPI)](https://junglewise.ai/threats/technologies/django): 173 vulnerabilities - [apache-airflow (PyPI)](https://junglewise.ai/threats/technologies/apache-airflow): 159 vulnerabilities - [pillow (PyPI)](https://junglewise.ai/threats/technologies/pillow): 125 vulnerabilities - [praisonai (PyPI)](https://junglewise.ai/threats/technologies/pypi-praisonai): 120 vulnerabilities - [vllm (PyPI)](https://junglewise.ai/threats/technologies/pypi-vllm): 117 vulnerabilities - [plone (PyPI)](https://junglewise.ai/threats/technologies/pypi-plone): 101 vulnerabilities - [mlflow (PyPI)](https://junglewise.ai/threats/technologies/mlflow): 88 vulnerabilities - [picklescan (PyPI)](https://junglewise.ai/threats/technologies/picklescan): 86 vulnerabilities ## Sources NVD, GitHub Security Advisories, OSV, the CISA Known Exploited Vulnerabilities catalog, FIRST EPSS and vendor advisories. Rebuilt every hour. Cite as: Junglewise Threat Intelligence, "lmdeploy (PyPI) vulnerabilities", https://junglewise.ai/threats/technologies/lmdeploy, 13 November 2026.