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.
Affected products
Version statuses are supplied by the assigning organization. Consult the original record for detailed ranges and platform conditions.
ggml-org llama.cpp
Default version status: unaffected
b8227 to < b11393affectedb11393unaffected
pkg:github/ggml-org/llama.cppReferences
- https://github.com/ggml-org/llama.cpp/pull/29942 ↗
- https://github.com/ggml-org/llama.cpp/commit/dbe4c3ed42343f0a7ba0fd7e808ffeaca404d29f ↗
- https://github.com/ggml-org/llama.cpp/blob/bed0a856606ee4a24a164066f73d2379447033f5/common/chat-peg-parser.cpp#L343-L355 ↗
- https://github.com/ggml-org/llama.cpp/blob/bed0a856606ee4a24a164066f73d2379447033f5/tools/server/server-schema.cpp#L321-L324 ↗
- https://github.com/ggml-org/llama.cpp ↗
- https://www.vulncheck.com/advisories/llama-cpp-before-b11393-use-after-free-via-common-chat-peg-mapper-chat-parser ↗