CVE-2026-107183

Published: Ott 07, 2026 Last Modified: Ott 07, 2026
ExploitDB:
Other exploit source:
Google Dorks:
CRITICAL 9,2
Source: [email protected]
Attack Vector: network
Attack Complexity: high
Privileges Required: none
User Interaction: none
Confidentiality: N/A
Integrity: N/A
Availability: N/A
HIGH 8,1
Source: [email protected]
Attack Vector: network
Attack Complexity: high
Privileges Required: none
User Interaction: none
Scope: unchanged
Confidentiality: high
Integrity: high
Availability: high

Description

AI Translation Available

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.

416

Use After Free

Stable
Abstraction: Variant Structure: Simple
Common Consequences
Security Scopes Affected:
Integrity Availability Confidentiality
Potential Impacts:
Modify Memory Dos: Crash, Exit, Or Restart Read Memory Execute Unauthorized Code Or Commands
Applicable Platforms
Languages: Memory-Unsafe, C, C++
Likelihood of Exploit: High
View CWE Details
https://github.com/ggml-org/llama.cpp
https://github.com/ggml-org/llama.cpp
https://github.com/ggml-org/llama.cpp/blob/bed0a856606ee4a2…
https://github.com/ggml-org/llama.cpp/blob/bed0a856606ee4a24a164066f73d23794470…
https://github.com/ggml-org/llama.cpp/blob/bed0a856606ee4a2…
https://github.com/ggml-org/llama.cpp/blob/bed0a856606ee4a24a164066f73d23794470…
https://github.com/ggml-org/llama.cpp/commit/dbe4c3ed42343f…
https://github.com/ggml-org/llama.cpp/commit/dbe4c3ed42343f0a7ba0fd7e808ffeaca4…
https://github.com/ggml-org/llama.cpp/pull/29942
https://github.com/ggml-org/llama.cpp/pull/29942
https://www.vulncheck.com/advisories/llama-cpp-before-b1139…
https://www.vulncheck.com/advisories/llama-cpp-before-b11393-use-after-free-via…