Skip to content

Forum

AI Assistant
Forums
Unread Posts
 
Notifications
Clear all

Unread Posts

 |  Forums  |  Topics
Page 89 / 148
Topics with their latest replies in reversed order
ELI5: Why can't the agent just ask me before it calls out?

By Chris P. 2 weeks ago  |  Last Post: 2 weeks ago

Forum Egress Filtering Configurations
Just finished a deep dive on the agent's file I/O - here's the map.

By Anna Lindberg 2 weeks ago  |  Last Post: 2 weeks ago

Forum Container and Runtime Hardening
How can I make sure Claude Code's suggestions don't introduce new vulns?

By Arjun Patel 2 weeks ago  |  Last Post: 2 weeks ago

Forum Claude Code Security
Hot take: Storing full prompt/responses for every inference is a lazy audit design.

By Ella Local 2 weeks ago  |  Last Post: 2 weeks ago

Forum Agent Audit Log Design
Check out what I made: A base image for Claw agents with all necessary libs.

By Jay R. 2 weeks ago  |  Last Post: 2 weeks ago

Forum MicroVMs and gVisor for Agent Isolation
Anyone else think Aider's chat commands introduce a dangerous attack surface?

By Priya S. 2 weeks ago  |  Last Post: 2 weeks ago

Forum Aider and OpenHands Security
Just built a canary token system that alerts if the agent tries to access a forbidden URL.

By Dana Foster 2 weeks ago  |  Last Post: 2 weeks ago

Forum Anthropic Agent SDK Security Surface
Just released a set of OPA/Rego policies for validating agent action requests.

By Hal Newb 2 weeks ago  |  Last Post: 2 weeks ago

Forum Show and Tell
How do I make sure the SDK isn't leaking my API keys in error logs?

By Gabe N. 2 weeks ago  |  Last Post: 2 weeks ago

Forum Anthropic Agent SDK Security Surface
Did you see the bypass using unicode homoglyphs in tool names?

By Oli Kernel 2 weeks ago  |  Last Post: 2 weeks ago

Forum OpenAI Operator Security
Page 89 / 148

 

 

 

Share:
Share
Tweet
Share