llama.cpp b2877 before b11935 ggml-rpc Server DoS via Oversized recv_msg Length
- Published
- Last modified
- Where the record stands: published, rejected by its publisher, or superseded by another id.What do these mean? →
- published
- Whether CISA lists it in its Known Exploited Vulnerabilities catalog: proof that attackers are using it.What do these mean? →
- Not listed in CISA KEV
- Fix
- Fixed in b11935
- Whether working attack code is public (Exploit-DB, Metasploit, Nuclei or GitHub). Public code makes attacks easier.What do these mean? →
- None on Exploit-DB, Metasploit or GitHub
- Exploitation: none
- Automatable: yes
- Technical impact: partial
Summary
The llama.cpp software's RPC server component (ggml-rpc, used via rpc-server) is affected. An unauthenticated remote attacker can send an oversized message to crash the server process, causing a denial of service for all connected clients.
Summarized by anthropic/claude-haiku-5.5. Verify details against the original sources.
Read the original description
llama.cpp b2877 before b11935 contains an uncaught exception vulnerability in the ggml-rpc server that allows unauthenticated remote attackers to crash the rpc-server by sending oversized message lengths. After the HELLO handshake, attackers can send a command such as SET_TENSOR with a length above std::vector::max_size(), triggering an uncaught std::length_error that aborts the process and denies service to all clients.
Timeline
- CVE published
- First seen by cve.now
- CISA SSVC assessment
Exploitation: none · Automatable: yes · Technical impact: partial
- Record last updated
Affected versions
- ggml-org llama.cpp
From b2877 · fixed in b11935