CVE Explorer
CVE-2026-21869
llama.cpp is an inference of several LLM models in C/C++. In commits 55d4206c8 and prior, the n_discard parameter is parsed directly from JSON input in the llama.cpp server's completion endpoints without validation to ensure it's non-negative. When a negative value is supplied and the context fills up, llama_memory_seq_rm/add receives a reversed range and negative offset, causing out-of-bounds memory writes in the token evaluation loop. This deterministic memory corruption can crash the process
Known exploited
Not asserted
Disputed
No
Stale source
No
Conflicts
0
Affected products and versions
1 source assertion{"product":"llama.cpp","vendor":"ggml-org","versions":[{"status":"affected","version":"<= 55d4206c8"}]}
- cve_program_cvelist_v5affectedurn:baitaphish:normalized-source-record:v2:bb010b7501af5ae730f9bfb9a84f604f5d87d7bea8cd2c22a768e65cfa1a119f · sha256:30ea4c5770141b3d… · /containers/cna/affected/0
Provider-owned CVSS observations
1 source assertion{"metric":{"attackComplexity":"LOW","attackVector":"NETWORK","availabilityImpact":"HIGH","baseScore":8.8,"baseSeverity":"HIGH","confidentialityImpact":"HIGH","integrityImpact":"HIGH","privilegesRequired":"NONE","scope":"UNCHANGED","userInteraction":"REQUIRED","vectorString":"CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H","version":"3.1"},"metric_type":"cvssV3_1"}
- cve_program_cvelist_v5cvssurn:baitaphish:normalized-source-record:v2:bb010b7501af5ae730f9bfb9a84f604f5d87d7bea8cd2c22a768e65cfa1a119f · sha256:30ea4c5770141b3d… · /containers/cna/metrics/0/cvssV3_1
CWE assertions
1 source assertion{"cweId":"CWE-787","description":"CWE-787: Out-of-bounds Write","lang":"en","type":"CWE"}
- cve_program_cvelist_v5cweurn:baitaphish:normalized-source-record:v2:bb010b7501af5ae730f9bfb9a84f604f5d87d7bea8cd2c22a768e65cfa1a119f · sha256:30ea4c5770141b3d… · /containers/cna/problemTypes/0/descriptions/0
Source references
2 source assertions{"name":"https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-8947-pfff-2f3c","tags":["x_refsource_CONFIRM"],"url":"https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-8947-pfff-2f3c"}
- cve_program_cvelist_v5referenceurn:baitaphish:normalized-source-record:v2:bb010b7501af5ae730f9bfb9a84f604f5d87d7bea8cd2c22a768e65cfa1a119f · sha256:30ea4c5770141b3d… · /containers/cna/references/0
{"tags":["exploit"],"url":"https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-8947-pfff-2f3c"}
- cve_program_cvelist_v5referenceurn:baitaphish:normalized-source-record:v2:bb010b7501af5ae730f9bfb9a84f604f5d87d7bea8cd2c22a768e65cfa1a119f · sha256:30ea4c5770141b3d… · /containers/adp/0/references/0
Attribution and limitations
- CVE Program CVEList V5: Reproduce the MITRE copyright designation and CVE license in copies. Source →
Provider severity values are preserved separately. Baitaphish does not convert them into a risk rating, infer affected products, or treat EPSS as observed exploitation.