llama.cpp before b3701 Out-of-Bounds Read in llama_decode via Token IDs
- 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- Where the record stands: published, rejected by its publisher, or superseded by another id.What do these mean?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 b3701
- 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 affected software is llama.cpp, an open-source library for running large language models, including its llama-server component. An unauthenticated remote attacker can exploit this flaw by sending specially crafted token IDs to the server, which can leak memory contents or crash the process.
Summarized by anthropic/claude-haiku-5.5. Verify details against the original sources.
Read the original description
llama.cpp before b3701 contains an out-of-bounds read vulnerability in llama_decode_internal and llama_encode_internal that allows remote unauthenticated attackers to read memory by supplying unvalidated token IDs. Attackers can send integer-array prompts to the llama-server /completion endpoint with IDs outside 0 to n_vocab to read embedding memory out of bounds or crash the process.
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
fixed in b3701