Activity
Mon
Wed
Fri
Sun
Nov
Dec
Jan
Feb
Mar
Apr
May
Jun
Jul
Aug
Sep
Oct
What is this?
Less
More
Owned by Larry
Learn how to use Claude desktop and Claude Code to connect your business apps, build AI agents, AI workflows, and create efficiencies with AI
1 contribution to AI Architects
2d •
Sandboxing and Other Subagent Security Measures?
Something I've neglected to pay attention to and became an issue recently when a sub agent launched by Claude used my email to register with an external service so that it could access information related to a task it was running. Not a big deal because I was researching security and the content was from OWASP, but I recognise how this could become a problem. Anyone got some suggestions here? I mainly use the Claude code extension in VS code but I also use open models via Ollama in the VS Code Chat
0 likes • 2d
@Stephen G. Pope main issue is that subagents head off on their tasks and there is no visibility on what they're doing until they return results. Inherit tools and permissions etc. from main agent and I could limit these but seems like a trade off between speed of getting tasks done and security. I'd like to have measures that prevent subagents from exposing data and info to external sources they shouldn't. I suppose there will always be a risk no matter the measures
0 likes • 1d
@Tylan Miller yes sure, but that could get exhausting. I’m thinking some boundaries that don’t slow progress too much. I want my cake and eat it too 🍰
1-1 of 1
@larry-maguire-1523
I’m a work & business psychologist, lecturer, AI skills trainer, career & business coach. I occupy the space where technology and people meet.
Active 2h ago
Joined Sep 7, 2026
Dublin
Powered by