CrewAI: Use of Externally-Controlled Input to Select Classes or Code
CVE-2026-92206 is a high-severity use of externally-controlled input to select classes or code vulnerability in CrewAI, with a CVSS 3.0 base score of 8.8 out of 10. It can be exploited remotely over the network by an unauthenticated attacker, but only if a user takes part, for example by opening a link or file. Affected CrewAI versions: Latest (as of 2025-10-09). The record does not name a fixed version, so check the vendor advisory. There is no confirmed exploitation so far. EPSS estimates a 0.46% chance of exploitation within 30 days, which is low compared with other CVEs.
High severity with no evidence of exploitation so far.
What to do
- Check which version of CrewAI you run against the affected versions below, and install the vendor's latest release.
- Until you can update, restrict network access to the affected service so it is not reachable from untrusted networks.
- Because the attack needs a user to take part, warn users about unexpected links and files related to this product until it is patched.
Affected products and versions
Version data comes from the organisation that assigned the CVE. Confirm against the vendor advisory before deciding you are unaffected.
How the severity score breaks down
- Attack vector
- NetworkCan be exploited remotely over a network, including the internet.
- Attack complexity
- LowNo special conditions are needed; the attack works reliably.
- Privileges required
- NoneNo account or login is needed.
- User interaction
- RequiredA user must take an action such as opening a file or link.
- Scope
- UnchangedImpact stays within the vulnerable component.
- Confidentiality
- HighAll data handled by the component can be read.
- Integrity
- HighData or code can be modified at will.
- Availability
- HighThe component can be taken down completely.
Vector: CVSS:3.0/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H. Scored by CNA (trendmicro.com).
Official description
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.
Source: the CVE record as published by its numbering authority, via NVD and CVE.org.
The underlying weakness: Use of Externally-Controlled Input to Select Classes or Code
The product uses external input with reflection to select which classes or code to use, but it does not sufficiently prevent the input from selecting improper classes or code.
How developers prevent this class of flaw
- Refactor your code to avoid using reflection.
- Do not use user-controlled inputs to select and load classes or code.
- Apply strict input validation by using allowlists or indirect selection to ensure that the user is only selecting allowable classes or code.
More Use of Externally-Controlled Input to Select Classes or Code vulnerabilities (CWE-470)
Timeline
- CVE record published.
- CISA published its SSVC assessment (exploitation: none, automatable: no, technical impact: total).
- Record last changed materially (score, affected products, status or references).
References
Other references
Other vulnerabilities in CrewAI
- 9.1 Critical severity
- 8.1 High severity
- 9.8 Critical severity
Recent Use of Externally-Controlled Input to Select Classes or Code vulnerabilities
- 7.3 High severity
- 9.8 Critical severity
- 7.0 High severity
- 8.8 High severity
- 7.8 High severity
- 8.5 High severity
Spotted an error? Tell us.