{"answers":{"affected":"3 open source packages ship an affected version, including lmdeploy.","exploited":"It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-46432 exists.","fix":"Upgrade lmdeploy to 0.13.0 or later.","what":"CVE-2026-46432 is a high-severity code injection vulnerability in InternLM lmdeploy, published on 9 Jun 2026. It can only be exploited from the same machine or local network, with no action from the victim."},"fix_prompt":"Check this codebase for CVE-2026-46432 and fix it if it is affected.\n\nWhat it is: CVE-2026-46432 is a high-severity code injection vulnerability in InternLM lmdeploy, published on 9 Jun 2026. It can only be exploited from the same machine or local network, with no action from the victim.\nExploitation: It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-46432 exists.\n\nAffected packages and fixed versions:\n- lmdeploy (PyPI): affected all versions; fixed in 0.13.0\n- lmdeploy (PyPI): affected all versions; fixed in 0.13.0\n- lmdeploy (PyPI): affected all versions; fixed in 0.13.0\n\nTask:\n1. Search the dependency manifests and lockfiles (for example package.json, package-lock.json, requirements.txt, poetry.lock, uv.lock, pom.xml, build.gradle, go.mod, Cargo.lock, Gemfile.lock) and any Dockerfiles for the affected packages, including transitive dependencies.\n2. If an affected version is in use, upgrade it to the fixed version for its release line with the project's package manager, so the lockfile is regenerated. Prefer the smallest upgrade that fixes it.\n3. If there is no fix, or the upgrade would break the build, do not guess: explain the risk and the safest workaround instead.\n4. Run the tests and summarise what changed and why.\n5. If nothing in the project is affected, say so and change nothing.\n\nReference: https://insights.sbomify.com/CVE-2026-46432/ (Markdown: https://insights.sbomify.com/CVE-2026-46432/index.md)","id":"CVE-2026-46432","markdown":"https://insights.sbomify.com/CVE-2026-46432/index.md","name":"CVE-2026-46432","record":{"aliases":["GHSA-m549-qq94-fvhg","PYSEC-2026-2609"],"analysis":{"component_type":"library","fix_type":"no_fix_stated","impacts":["code_execution"],"network_reachable":"adjacent_or_local","non_default_config":false,"product_category":"LLM deployment toolkit","requires_auth":"low_privilege","summary":"Attackers can execute arbitrary code by exploiting hardcoded trust_remote_code settings in LMDeploy's model initialization process.","user_interaction":"not_required","vuln_class":"code_injection"},"analysis_generated_by":"qwen3.8-flash-next","assigner":"GitHub_M","cpe":[],"cvss":{"score":7.8,"severity":"high","source":"cna","vector":"CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H","version":"3.1"},"cwes":[{"id":"CWE-94","name":"Improper Control of Generation of Code"}],"description":"LMDeploy is a toolkit for compressing, deploying, and serving large language models. In versions 0.12.3 and prior, LMDeploy is vulnerable to arbitrary code execution through hardcoded \"trust_remote_code=True\" in multiple HuggingFace model-loading call sites. At time of publication, there are no publicly available patches.","ecosystems":["PyPI"],"exploits":{"exploitdb":0,"first_seen":null,"github_poc":0,"max_poc_stars":null,"metasploit":0,"nuclei":0,"refs":[],"tier":"weaponised"},"has_fix":true,"headline":"LMDeploy: Arbitrary code execution via hardcoded trust_remote_code=True in lmdeploy model initialization","id":"CVE-2026-46432","indexable":true,"kev":null,"kind":"cve","links":{"ecosystem":"PyPI","product":null,"products":[],"type":"code_injection","year":"2026"},"n_packages":3,"n_references":1,"next":{"headline":"lldpd: Heap OOB Read in VLAN Decapsulation memmove","id":"CVE-2026-46433"},"packages":[{"ecosystem":"PyPI","fixed":["0.13.0"],"introduced":["0"],"last_affected":[],"package":"lmdeploy","purl":null,"source":"GHSA-m549-qq94-fvhg"},{"ecosystem":"PyPI","fixed":["0.13.0"],"introduced":["0"],"last_affected":[],"package":"lmdeploy","purl":"pkg:pypi/lmdeploy","source":"GHSA-m549-qq94-fvhg"},{"ecosystem":"PyPI","fixed":["0.13.0"],"introduced":["0"],"last_affected":[],"package":"lmdeploy","purl":"pkg:pypi/lmdeploy","source":"PYSEC-2026-2609"}],"prev":{"headline":"Algernon: Auto-refresh SSE event server sets Access-Control-Allow-Origin: *","id":"CVE-2026-46431"},"products":["lmdeploy"],"published":"2026-06-09","related":[],"sources":[{"class":"attribution","licence":"CVE Terms of Use (MITRE)","name":"CVE List","prefix":"CVE"},{"class":"attribution","licence":"CC BY 4.0","name":"GitHub Advisory Database","prefix":"GHSA"},{"class":"attribution","licence":"CC BY 4.0","name":"PyPA Advisory Database","prefix":"PYSEC"},{"class":"attribution","licence":"CWE Terms of Use","name":"CWE (MITRE)"},{"class":"attribution","licence":"FIRST CVSS licence","name":"CVSS (FIRST)"}],"ssvc":{"automatable":"no","exploitation":"poc","technical_impact":"total"},"state":"PUBLISHED","updated":"2026-06-11","vendors":["InternLM"]},"summary":"Attackers can execute arbitrary code by exploiting hardcoded trust_remote_code settings in LMDeploy's model initialization process.","url":"https://insights.sbomify.com/CVE-2026-46432/"}