CVE-2026-75090: Out-of-Bounds Read in EricLBuehler Mistral.rs
CVE-2026-75090 is a medium severity vulnerability in EricLBuehler Mistral.rs up to version 0.8.22. It involves an out-of-bounds read in the convert_gguf_to_hf_tokenizer function within the GGUF Tokenizer component. The issue arises from manipulation of the eos_token_id, bos_token_id, or unknown_token_id arguments. This vulnerability can be exploited remotely and public exploit code is available. Upgrading to version 0.8.23 resolves the issue.
AI Analysis
Technical Summary
An out-of-bounds read vulnerability exists in the convert_gguf_to_hf_tokenizer function of the GGUF Tokenizer component in EricLBuehler Mistral.rs versions up to 0.8.22. The flaw is triggered by manipulating the eos_token_id, bos_token_id, or unknown_token_id arguments, leading to memory access beyond intended bounds. The vulnerability is remotely exploitable, and public exploit code has been released. The issue is fixed in version 0.8.23 with patch cd5297e2ea5cb27c790bdcf2f3c2f1064a81d55e.
Potential Impact
Successful exploitation can cause out-of-bounds memory reads, potentially leading to information disclosure or application instability. The vulnerability is remotely exploitable without privileges or user interaction, increasing risk. The CVSS 4.0 base score is 5.3 (medium severity).
Mitigation Recommendations
Upgrade EricLBuehler Mistral.rs to version 0.8.23 or later, which contains the official fix for this vulnerability. No other mitigations are indicated.
CVE-2026-75090: Out-of-Bounds Read in EricLBuehler Mistral.rs
Description
CVE-2026-75090 is a medium severity vulnerability in EricLBuehler Mistral.rs up to version 0.8.22. It involves an out-of-bounds read in the convert_gguf_to_hf_tokenizer function within the GGUF Tokenizer component. The issue arises from manipulation of the eos_token_id, bos_token_id, or unknown_token_id arguments. This vulnerability can be exploited remotely and public exploit code is available. Upgrading to version 0.8.23 resolves the issue.
CVSS v4.0
Score 5.3medium
Affected software
EricLBuehler
Mistral.rs
pkg:cargo/github/EricLBuehler/mistral.rscpe:2.3:a:ericlbuehler:mistral.rs:*:*:*:*:*:*:*:*Run on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
An out-of-bounds read vulnerability exists in the convert_gguf_to_hf_tokenizer function of the GGUF Tokenizer component in EricLBuehler Mistral.rs versions up to 0.8.22. The flaw is triggered by manipulating the eos_token_id, bos_token_id, or unknown_token_id arguments, leading to memory access beyond intended bounds. The vulnerability is remotely exploitable, and public exploit code has been released. The issue is fixed in version 0.8.23 with patch cd5297e2ea5cb27c790bdcf2f3c2f1064a81d55e.
Potential Impact
Successful exploitation can cause out-of-bounds memory reads, potentially leading to information disclosure or application instability. The vulnerability is remotely exploitable without privileges or user interaction, increasing risk. The CVSS 4.0 base score is 5.3 (medium severity).
Mitigation Recommendations
Upgrade EricLBuehler Mistral.rs to version 0.8.23 or later, which contains the official fix for this vulnerability. No other mitigations are indicated.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- VulDB
- Date Reserved
- 2026-08-17T16:35:41.582Z
- Cvss Version
- 4.0
- State
- PUBLISHED
Threat ID: 6a83bbd9bf8831d539fd23f5
Added to database: 08/18/2026, 01:56:41 UTC
Last enriched: 09/11/2026, 23:32:28 UTC
Last updated: 10/02/2026, 02:46:06 UTC
Views: 68
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
Need more coverage?
Upgrade to Pro Console for AI refresh and higher limits.
For incident response and remediation, OffSeq services can help resolve threats faster.
Latest Threats
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.