llama.cpp builds b7492 through the latest b9060 contains a use-after-free vulnerability in llama-server affecting six tokenization endpoints (/tokenize, /detokenize, /infill, /apply-template, /rerank, and /anthropic/count_tokens) that bypass the task queue and access ctx_server.vocab directly on HTTP worker threads. Attackers can exploit a time-of-check-time-of-use race condition where the main thread destroys and frees vocab after the synchronization lock is released but before the handler finishes using it, causing a crash or potential code execution when --sleep-idle-seconds is configured.
Attack Parameters
Attack Vector
Network
Can be exploited remotely
Attack Complexity
High
Difficult to exploit
Attack Requirements
Present
Additional conditions required
Privileges Required
None
No privileges needed
User Interaction
None
No user interaction needed
Impact Assessment
Confidentiality
High
Complete data leak
Integrity
High
Complete data modification
Availability
High
Complete denial of service
CVSS Vector v4.0
Weakness Type (CWE)
Vulnerable Products
ggml-org:llama.cpp