Forum

Forums
Non-Claw Alternativ...
Code-First Agent Fr...
CrewAI and AutoGen ...
 
Notifications
Clear all

CrewAI and AutoGen Security

Security analysis of CrewAI and AutoGen — inter-agent messaging trust, code execution in AutoGen's code-running agents, role and permission design in CrewAI crews, and default-unsafe patterns in both.
RSS
Page 2 / 5

Did you see the CVE-2025-XXXX for CrewAI's insecure secret handling?

Last post by Oliver Jones, 1 month ago

Posts: 8
Views: 5


Unpopular opinion: You don't need enclave-level security for local CrewAI if you control the host

Last post by Priya S., 1 month ago

Posts: 4
Views: 6


Check out my talk at BSides on abusing AutoGen's insecure tool calling

Last post by Dave 'R00t' Miller, 1 month ago

Posts: 1
Views: 6


Is there a way to disable the default code execution in AutoGen entirely?

Last post by Tom L., 1 month ago

Posts: 1
Views: 6


What are the security implications of using CrewAI's default credential store?

Last post by Lei C., 2 months ago

Posts: 1
Views: 5


Sharing a proof-of-concept of a prompt injection that leaks all agent secrets in CrewAI

Last post by Ben Kowalski, 2 months ago

Posts: 1
Views: 7


Guide: Using container isolation (Docker/Podman) for each AutoGen agent

Last post by Finn O'Rourke, 2 months ago

Posts: 6
Views: 4


Thoughts on the claim that CrewAI is 'secure by design' in the latest release notes?

Last post by audit_log_priya, 2 months ago

Posts: 25
Views: 9


How do I set up role-based permissions for human-in-the-loop in CrewAI?

Last post by Oli N., 2 months ago

Posts: 22
Views: 17


Just built a security linter that scans CrewAI configs for unsafe defaults

Last post by Ivy Policy, 2 months ago

Posts: 19
Views: 12


Page 2 / 5
Share:
Share
Tweet
Share