{"answers":{"affected":"It affects 1 product.","exploited":"It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-34159 exists.","fix":"Upgrade to a fixed version.","what":"CVE-2026-34159 is a critical memory corruption vulnerability in ggml-org llama.cpp, published on 1 Apr 2026. An attacker can exploit it over the internet without logging in, with no action from the victim."},"fix_prompt":"Check this codebase for CVE-2026-34159 and fix it if it is affected.\n\nWhat it is: CVE-2026-34159 is a critical memory corruption vulnerability in ggml-org llama.cpp, published on 1 Apr 2026. An attacker can exploit it over the internet without logging in, with no action from the victim.\nExploitation: It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-34159 exists.\n\nAffected product: ggml-org llama.cpp. No package-level version data is available, so check the vendor advisory linked from the reference page.\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-2026-34159/ (Markdown: https://insights.sbomify.com/CVE-2026-34159/index.md)","id":"CVE-2026-34159","markdown":"https://insights.sbomify.com/CVE-2026-34159/index.md","name":"CVE-2026-34159","record":{"aliases":["DEBIAN-CVE-2026-34159","GHSA-j8rj-fmpv-wcxw","UBUNTU-CVE-2026-34159"],"analysis":{"component_type":"library","fix_type":"upgrade","impacts":["code_execution"],"network_reachable":"yes","non_default_config":false,"product_category":"LLM inference library","requires_auth":"none","summary":"Unauthenticated attackers can achieve remote code execution in llama.cpp RPC backend via memory corruption in tensor deserialization.","user_interaction":"not_required","vuln_class":"memory_corruption"},"analysis_generated_by":"qwen3.8-flash-next","assigner":"GitHub_M","cpe":[{"product":"llama.cpp","vendor":"ggml"}],"cvss":{"score":9.8,"severity":"critical","source":"cna","vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H","version":"3.1"},"cwes":[{"id":"CWE-119","name":"Improper Restriction of Operations within the Bounds of a Memory Buffer"}],"description":"llama.cpp is an inference of several LLM models in C/C++. Prior to version b8492, the RPC backend's deserialize_tensor() skips all bounds validation when a tensor's buffer field is 0. An unauthenticated attacker can read and write arbitrary process memory via crafted GRAPH_COMPUTE messages. Combined with pointer leaks from ALLOC_BUFFER/BUFFER_GET_BASE, this gives full ASLR bypass and remote code execution. No authentication required, just TCP access to the RPC server port. This issue has been patched in version b8492.","ecosystems":[],"exploits":{"exploitdb":0,"first_seen":"2026-04-23","github_poc":3,"max_poc_stars":28,"metasploit":0,"nuclei":0,"refs":[{"date":"2026-04-23T21:14:21Z","kind":"github_poc","ref":"https://github.com/casp3r0x0/CVE-2026-34159","stars":28,"title":"0 Click RCE exploit for CVE-2026-34159 Lama.cpp RPC server"},{"date":"2026-05-04T08:59:55Z","kind":"github_poc","ref":"https://github.com/rohithronanki/CVE-2026-34159-Vulnerability-Research-Analysis-Detection","stars":0,"title":"Critical buffer validation bypass in deserialize_tensor() (llama.cpp \u003c b8492). Null tensor buffer skips bounds check, enabling unauthenticated arbitrary R/W via GRAPH_COMPUTE. ASLR bypass + RCE over TCP 50052."},{"date":"2026-08-27T02:53:08Z","kind":"github_poc","ref":"https://github.com/TeamN4C/SG-2026-0021","stars":0,"title":"CVE-2026-34159 PoC and exploit"}],"tier":"weaponised"},"has_fix":true,"headline":"llama.cpp: Unauthenticated RCE via GRAPH_COMPUTE buffer=0 bypass in llama.cpp RPC backend","id":"CVE-2026-34159","indexable":true,"kev":null,"kind":"cve","links":{"ecosystem":null,"product":null,"products":[],"type":"memory_corruption","year":"2026"},"n_packages":0,"n_references":3,"next":{"headline":"Server-side request forgery in chamilo-lms","id":"CVE-2026-34160"},"packages":[],"prev":{"headline":"Coolify: Command injection via single-quote breakout in Docker Compose custom commands","id":"CVE-2026-34158"},"products":["llama.cpp"],"published":"2026-04-01","related":[{"cvss_score":10,"headline":"llama.cpp allows write-what-where in rpc_server::set_tensor","id":"CVE-2024-42479","kev_date_added":null,"published":"2024-08-12"},{"cvss_score":9.2,"headline":"llama.cpp b4882–b9058 Buffer Overflow in KV Cache State Restore","id":"CVE-2026-43629","kev_date_added":null,"published":"2026-08-06"},{"cvss_score":9.2,"headline":"llama.cpp b7492–b9060 Use-After-Free RCE via llama-server","id":"CVE-2026-43631","kev_date_added":null,"published":"2026-08-06"},{"cvss_score":9.2,"headline":"llama.cpp b7492–b9060 Use-After-Free in Tokenization Endpoints","id":"CVE-2026-43632","kev_date_added":null,"published":"2026-08-06"},{"cvss_score":8.8,"headline":"llama.cpp has Out-of-bounds Write in llama-server","id":"CVE-2026-21869","kev_date_added":null,"published":"2026-01-07"},{"cvss_score":8.8,"headline":"llama.cpp Vulnerable to Buffer Overflow via Malicious GGUF Model","id":"CVE-2025-49847","kev_date_added":null,"published":"2025-06-17"}],"sources":[{"class":"attribution","licence":"CVE Terms of Use (MITRE)","name":"CVE List","prefix":"CVE"},{"class":"attribution","licence":"US public information, NVD API terms","name":"NVD"},{"class":"attribution","licence":"CWE Terms of Use","name":"CWE (MITRE)"},{"class":"attribution","licence":"FIRST CVSS licence","name":"CVSS (FIRST)"},{"class":"open","licence":"CC0","name":"PoC-in-GitHub"}],"ssvc":{"automatable":"yes","exploitation":"poc","technical_impact":"total"},"state":"PUBLISHED","updated":"2026-04-02","vendors":["ggml-org"]},"summary":"Unauthenticated attackers can achieve remote code execution in llama.cpp RPC backend via memory corruption in tensor deserialization.","url":"https://insights.sbomify.com/CVE-2026-34159/"}