llama.cpp: Use After Free
CVE-2026-107183 is a high-severity use after free vulnerability in llama.cpp from Ggml-org, with a CVSS 3.1 base score of 8.1 out of 10. It can be exploited remotely over the network by an unauthenticated attacker, without any action from a user. The record lists version b11393 as the first without the flaw, so updating llama.cpp to that release or later removes the exposure. There is no confirmed exploitation so far. EPSS estimates a 0.42% chance of exploitation within 30 days, which is low compared with other CVEs.
High severity with no evidence of exploitation so far.
What to do
- Update llama.cpp to b11393 or a later version.
- Until you can update, restrict network access to the affected service so it is not reachable from untrusted networks.
Affected products and versions
Version data comes from the organisation that assigned the CVE. Confirm against the vendor advisory before deciding you are unaffected.
How the severity score breaks down
- Attack vector
- NetworkCan be exploited remotely over a network, including the internet.
- Attack complexity
- HighSuccess depends on conditions outside the attacker's control.
- Privileges required
- NoneNo account or login is needed.
- User interaction
- NoneNo action by a victim is required.
- Scope
- UnchangedImpact stays within the vulnerable component.
- Confidentiality
- HighAll data handled by the component can be read.
- Integrity
- HighData or code can be modified at will.
- Availability
- HighThe component can be taken down completely.
Vector: CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H. Scored by CNA (vulncheck.com).
| Scoring system | Score | Severity | Scored by |
|---|---|---|---|
| CVSS 4.0 | 9.2 | Critical | CNA (vulncheck.com) |
| CVSS 3.1 | 8.1 | High | CNA (vulncheck.com) |
Official 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.
Source: the CVE record as published by its numbering authority, via NVD and CVE.org.
The underlying weakness: Use After Free
The product reuses or references memory after it has been freed. At some point afterward, the memory may be allocated again and saved in another pointer, while the original pointer references a location somewhere within the new allocation. Any operations using the original pointer are no longer valid because the memory belongs to the code that operates on the new pointer.
How developers prevent this class of flaw
- Choose a language that provides automatic memory management.
- When freeing pointers, be sure to set them to NULL once they are freed. However, the utilization of multiple or complex data structures may lower the usefulness of this strategy.
Timeline
- CVE record published.
- CISA published its SSVC assessment (exploitation: none, automatable: no, technical impact: total).
References
Patches and release notes
Other references
- github.com/ggml-org/llama.cpp
- github.com/ggml-org/llama.cpp/blob/bed0a856606ee4a24a164066f73d2379447033f5/common/chat-peg-parser.cpp#L343-L…
- github.com/ggml-org/llama.cpp/blob/bed0a856606ee4a24a164066f73d2379447033f5/tools/server/server-schema.cpp#L3…
- vulncheck.com/advisories/llama-cpp-before-b11393-use-after-free-via-common-chat-peg-mapper-chat-parser
Other vulnerabilities in llama.cpp
- 7.5 High severity
- 8.1 High severity
- 7.8 High severity
- 8.2 High severity
- 7.3 High severity
- 7.0 High severity
Recent Use After Free vulnerabilities
- 9.8 Critical severity
- 8.8 High severity
- 8.8 High severity
- 9.6 Critical severity
- 8.8 High severity
- 8.3 High severity
Spotted an error? Tell us.