CrewAI: Remote code execution via unsafe module import in agent loading
Summary
CrewAI, an open-source framework for multi-agent workflows, contains an unsafe reflection flaw in the load_agent_from_repository function. A user-supplied argument is not sufficiently restricted before it is used to import a module. If a victim loads a malicious agent configuration from a repository, an attacker can execute arbitrary code in the context of the service account. The vulnerability is publicly disclosed as a zero-day, and no vendor fix has been confirmed.
Affected
- CrewAI (product listed as CrewAI, version listed only as "Latest (as of 2025-10-09)"; exact affected version range unknown)
Fixed in
- Unknown. No vendor fix or fixed version has been confirmed.
Workaround
- The only mitigation named by ZDI is to restrict interaction with the product.
- Do not load agent configurations from repositories or sources you do not fully control.
Exploitation
- ZDI published the advisory as a 0-day; no evidence of exploitation in the wild found.
- CISA SSVC: Exploitation none, Automatable no, Technical Impact total.
- Not listed in the KEV catalog.
- No public proof of concept found.
Our recommendation
- Treat CrewAI as unpatched until the vendor confirms a fix.
- Do not load agent configurations from repositories or endpoints you do not fully control.
- Run CrewAI with least privilege and a restricted service account.
- Monitor for use of from_repository in agent YAML or JSON files and review CI and development hosts.
- Check the vendor and GitHub regularly for a security advisory or fixed release.
Public exploits
PoC-in-GitHub, Metasploit and Exploit-DB list nothing for this CVE.
Research sources
- ZDI-26-706 Advisory www.zerodayinitiative.com
- CrewAI GitHub issue #7995 github.com
- CrewAI agent repositories documentation docs.crewai.com
- OpenCVE CVE-2026-92206 app.opencve.io
- VulnCheck/Vulners VULNRICHMENT CVE-2026-92206 vulners.com
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 31 Oct 2026, 11:08.
Original description (NVD)
CrewAI crewAI Framework Agent Loading Unsafe Reflection Remote Code Execution Vulnerability. This vulnerability allows remote attackers to execute arbitrary code on affected installations of CrewAI crewAI. User interaction is required to exploit this vulnerability in that the target must load a malicious agent configuration from the repository. The specific flaw exists within the load_agent_from_repository function. The process does not properly restrict a user-supplied argument before using it to import a module. An attacker can leverage this vulnerability to execute code in the context of the service account. Was ZDI-CAN-28387.
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.