Remote code execution via silent sandbox fallback
Published Mar 30, 2026 · Updated Mar 30, 2026
Code injection in CrewAI 1.0 allows remote attackers to execute code on the host through prompt input to an enabled CodeInterpreterTool. CodeInterpreterTool checks Docker availability for each execution but silently routes code to SandboxPython when Docker is unavailable, replacing container isolation with bypassable Python restrictions. Exploitation requires direct or indirect prompt influence over an agent with code execution enabled and a Docker outage or loss of access during operation.
Summary
What happened
Code injection in CrewAI 1.0 allows remote attackers to execute code on the host through prompt input to an enabled CodeInterpreterTool. CodeInterpreterTool checks Docker availability for each execution but silently routes code to SandboxPython when Docker is unavailable, replacing container isolation with bypassable Python restrictions. Exploitation requires direct or indirect prompt influence over an agent with code execution enabled and a Docker outage or loss of access during operation.
The record
- CVE
- CVE-2026-2287
- Published
- Mar 30, 2026
- Updated
- Mar 30, 2026
- Vendor
- CrewAI
- Product
- CrewAI
- Classifications
- CWE-94, T1059.006
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Mar 30, 2026CVE publishedPublication date reported by the CVE source.
- Mar 30, 2026Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=1.0
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
No public exploit references are available in this record.
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo