---
id: "CVE-2026-124028"
page: "https://infrastack.ai/live/CVE-2026-124028"
kind: "vulnerability"
aliases: ["CVE-2026-124028"]
title: "mistral.rs: delimiter injection lets attackers forge tool calls before 0.9.5"
severity: "medium"
cvss: 4.2
epss: null
exploited: false
status: "open"
category: "ai-tooling"
products: []
ecosystems: []
tags: ["ai-tooling", "llm-serving", "mistral.rs", "rust", "tool-calling"]
not_affected_if: ["no-tool-calling", "trusted-input-only"]
published_at: "2026-11-06T20:17:21+00:00"
first_seen_at: "2026-11-06T20:43:59+00:00"
updated_at: "2026-11-06T20:44:25+00:00"
sources: [{"source": "nvd", "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-124028", "first_seen_at": "2026-11-06T20:43:59+00:00"}]
exploit_sources: []
---

# mistral.rs: delimiter injection lets attackers forge tool calls before 0.9.5

Link for people: https://infrastack.ai/live/CVE-2026-124028 (this .md is for agents)

Before version 0.9.5, mistral.rs's mistralrs-core treats delimiter strings such as </tool_call> in model-quoted text as real tool-call markers. An attacker who controls documents, web pages or tool outputs can make the qwen-xml, gemma4 or reasoning parsers return extra calls to declared tools with attacker-chosen arguments.

_Summary, check and fix written by a model from the sources; labelled as such._

## How to check

- Check the installed mistralrs or mistralrs-core version; anything below `0.9.5` is in range.
- Look for use of the qwen-xml, gemma4 or reasoning parsers in your serving config.
- Confirm whether the model reads untrusted documents, web pages or tool outputs.

## Fix

- mistral.rs: upgrade to `0.9.5` or later.

## Timeline

- 2026-11-06T20:43:59+00:00 nvd https://nvd.nist.gov/vuln/detail/CVE-2026-124028

## Documents

- [advisory] Vendor advisory: github.com https://github.com/EricLBuehler/mistral.rs/security/advisories/GHSA-34w8-j94f-8c5w
- [advisory] Third-party advisory: www.vulncheck.com https://www.vulncheck.com/advisories/mistral-rs-before-0.9.5-tool-call-injection-via-mistralrs-core-output-parsers
- [fix] Patch: github.com https://github.com/EricLBuehler/mistral.rs/commit/b43d3443e946752c0f662c2df42a2974410c9532
- [fix] Release notes: github.com https://github.com/EricLBuehler/mistral.rs/releases/tag/v0.9.5

## From the sources

mistral.rs before 0.9.5 contains a delimiter injection vulnerability in mistralrs-core that allows attackers to inject tool calls by placing delimiter strings in text the model quotes. Attackers controlling documents, web pages or tool outputs can embed tags like </tool_call> to make qwen-xml, gemma4 or reasoning parsers return extra calls to declared tools with attacker-chosen arguments.

---

_Free to read, with fair use of about 60 pages a minute. For higher limits or API access: sales@infrastack.ai_