Ultralytics: Code injection in parse_model leads to remote code execution
Summary
The Python library Ultralytics, used for YOLO computer-vision models, contains a code injection flaw in the parse_model function. The function executes a user-supplied string as Python code without proper validation. An attacker who gets a user to open a malicious model file or visit a malicious page can run arbitrary code with that user's privileges. The CVSS vector is rated local, but the advisory describes remote attackers, so the more serious reading should be assumed.
Affected
- Ultralytics 8.4.65 (according to the CVE record and VulDB)
- Other versions: Unknown.
Fixed in
Unknown. No vendor advisory or fixed version was found at the time of research.
Workaround
- The ZDI advisory states that the only salient mitigation is to restrict interaction with the product.
- Do not load model files, configurations or other inputs from untrusted sources.
- Run Ultralytics in an isolated environment (separate VM or container, without access to credentials or sensitive data).
Exploitation
- No known exploitation in the wild; not listed in CISA KEV.
- No public exploit code indexed at the time of research.
- EPSS: 0.22 % (percentile 13).
Our recommendation
- Inventory Python environments for the package ultralytics (for example with pip show ultralytics) and record the versions.
- Identify systems that load externally sourced models or configurations and restrict them until a fix is available.
- Treat PyTorch model files from untrusted sources as potentially unsafe code.
- Monitor the Ultralytics GitHub releases, the ZDI advisory and the NVD entry for a fix.
- Do not assume that any other Ultralytics advisory fixes this issue.
Public exploits
PoC-in-GitHub, Metasploit and Exploit-DB list nothing for this CVE.
Research sources
- ZDI advisory ZDI-26-817 www.zerodayinitiative.com
- Strix CVE record CVE-2026-118618 www.strix.ai
- VulDB entry 428056 vuldb.com
- OffSeq exploitation and KEV status radar.offseq.com
- Threat research summary threatresearch.io
Researched and written up in English and German by an AI (Claude by Anthropic) based on NVD, CISA, EPSS and the sources listed. The vendor information is authoritative. Researched on 1 Nov 2026, 21:50.
Original description (NVD)
Ultralytics parse_model Code Injection Remote Code Execution Vulnerability. This vulnerability allows remote attackers to execute arbitrary code on affected installations of Ultralytics. User interaction is required to exploit this vulnerability in that the target must visit a malicious page or open a malicious file. The specific flaw exists within the parse_model function. The issue results from the lack of proper validation of a user-supplied string before using it to execute Python code. An attacker can leverage this vulnerability to execute code in the context of the current user. Was ZDI-CAN-30121.
NVD references (1)
Sources
The tracker combines official, freely usable data sources – updated continuously:
- NVD (NIST) – CVEs, rating (CVSS), affected products
- CISA KEV – vulnerabilities confirmed by CISA as actively exploited
- CISA Vulnrichment – CISA assessment (SSVC) in the official CVE record
- FIRST EPSS – probability of exploitation
- Microsoft MSRC – Patch Tuesday: vulnerabilities, severity, updates
- PoC-in-GitHub – public proof-of-concept repositories
- Metasploit (Rapid7) – modules of the Metasploit Framework
- Exploit-DB (OffSec) – archive of public exploits (links only)
- Patch days: official vendor pages (linked per vendor) (Vendor patch days)
This product uses data from the NVD API but is not endorsed or certified by the NVD. EPSS data © FIRST.org.
Affected? We can help.
We check whether your systems are affected, install updates and close the gap – continuously with the System Health Checker if you wish.