llama.cpp before b11393 Use-After-Free via common_chat_peg_mapper chat_parser
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.
CVE-2026-107183
Primary source · Revision 1
Imported from structured advisory data. Source references identify upstream records or fields; verify affected versions and your deployed configuration.
Security context
Source reference: cve:CVE-2026-107183
llama.cpp
Source reference: /containers/cna/affected/0/product
- Affected versions
- Not stated in this record
- Fixed versions
- Not stated in this record
- Prerequisites
- Not stated in this record
Structured affected-version data
Original package identities and version rules from this source.
[
{
"vendor": "ggml-org",
"product": "llama.cpp",
"versions": [
{
"status": "affected",
"version": "b8227",
"lessThan": "b11393",
"versionType": "custom"
},
{
"status": "unaffected",
"version": "b11393",
"versionType": "custom"
}
],
"packageURL": "pkg:github/ggml-org/llama.cpp",
"defaultStatus": "unaffected"
}
]- Related CVEs
- CVE-2026-107183
Source reference:
/cveMetadata/cveId
Publisher severity
critical
Source reference: /containers/cna/metrics
- Event
- #11875 · Revision 1
- Added to Heist Feed
- Publisher date