Forum

Forums
The Claw Family
NanoClaw — Containe...
Anthropic Agent SDK...
 
Notifications
Clear all

Anthropic Agent SDK Security Surface

Security properties inherited from and introduced by the Anthropic Agent SDK — API authentication, tool permission grants, and what Anthropic's hosted components see versus what stays local.
RSS
Page 2 / 3

Am I the only one who thinks the default permission model is too permissive?

Last post by Sasha O'Neill, 1 month ago

Posts: 6
Views: 6


What is the best way to validate and sanitize tool inputs before the SDK sends them?

Last post by Yuki Nakamura, 2 months ago

Posts: 7
Views: 11


Showcase: My custom permission layer that sits between the SDK and my tools.

Last post by Zoey Dev, 2 months ago

Posts: 3
Views: 7


What tools are you absolutely *not* exposing to the agent, and why?

Last post by Nadia Fischer, 2 months ago

Posts: 1
Views: 6


Anyone else having issues with tool execution timing out and leaving processes hanging?

Last post by Priya K., 2 months ago

Posts: 2
Views: 7


Switching tools at runtime based on user role - how to do this securely with the SDK?

Last post by Laura Chen, 2 months ago

Posts: 20
Views: 13


Thoughts on the new agent memory feature - what data persistence risks does it add?

Last post by Maya L., 2 months ago

Posts: 20
Views: 10


Does the SDK's streaming response feature leak partial tool results?

Last post by Hannah Müller, 2 months ago

Posts: 25
Views: 11


Does the SDK's built-in 'human in the loop' approval send conversation context to Anthropic?

Last post by Rae Chen, 2 months ago

Posts: 6
Views: 12


Is it safe to use the SDK's built-in 'filesystem' tool examples in production? (No.)

Last post by smart_home_raj, 2 months ago

Posts: 4
Views: 9


Page 2 / 3
Share:
Share
Tweet
Share