Login Request a demo
High severity · published Oct 7, 2026
CVE-2026-107183
llama.cpp before b11393 Use-After-Free via common_chat_peg_mapper chat_parser
8.1
CVSS
0.4%
EPSS
No
On KEV
Description
llama.cpp before b11393 contains a use-after-free and double free vulnerability in common_chat_peg_mapper::map that allows unauthenticated remote attackers to corrupt heap memory via a dangling current_tool pointer. Attackers can submit a chat_parser in a POST /completion request emitting a tool-id after a tool-close tag to crash llama-server and shape a heap write primitive.
CVSS vector
CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H
Attack vector
Network
Complexity
High
Privileges
None
User interaction
None
Confidentiality
High
Integrity
High
Availability
High
Scope
Unchanged
Exploitation
Is it being used?
Exploit prediction (EPSS)0.4% · higher than 36% of CVEs
Exploited in the wildNo evidence yet
CISA KEVNot listed
Ransomware campaign useNot known
Affected products
Which versions
LL
llama.cpp · ggml-org
b8227 before b11393 · source: vendor
Affected product
LL
llama.cpp
ggml-org
References
NVD
https://nvd.nist.gov/vuln/detail/CVE-2026-107183
CVE.org
https://www.cve.org/CVERecord?id=CVE-2026-107183
patch
https://github.com/ggml-org/llama.cpp/pull/29942
patch
https://github.com/ggml-org/llama.cpp/commit/dbe4c3ed42343f0a7ba0fd7e808ffeaca404d29f
technical-description
https://github.com/ggml-org/llama.cpp/blob/bed0a856606ee4a24a164066f73d2379447033f5/common/chat-peg-parser.cpp#L343-L355
technical-description
https://github.com/ggml-org/llama.cpp/blob/bed0a856606ee4a24a164066f73d2379447033f5/tools/server/server-schema.cpp#L321-L324
product
https://github.com/ggml-org/llama.cpp
third-party-advisory
https://www.vulncheck.com/advisories/llama-cpp-before-b11393-use-after-free-via-common-chat-peg-mapper-chat-parser
More from llama.cpp
9.8
CVE-2026-34159
llama.cpp: Unauthenticated RCE via GRAPH_COMPUTE buffer=0 bypass in llama.cpp RPC backend
9.8
CVE-2026-21869
llama.cpp has Out-of-bounds Write in llama-server
8.2
CVE-2024-58400
llama.cpp before b3701 Out-of-Bounds Read in llama_decode via Token IDs
8.1
CVE-2026-118375
llama.cpp b8841 before b11865 Stack-based Buffer Overflow via ggml-rpc RDMA rdma_recv()
8.1
CVE-2026-43632
llama.cpp b7492–b9060 Use-After-Free in Tokenization Endpoints