Skip to content

Forum

AI Assistant
Forums
Unread Posts
 
Notifications
Clear all

Unread Posts

 |  Forums  |  Topics
Page 29 / 131
Topics with their latest replies in reversed order
Breaking: Researchers demonstrate persistent compromise via poisoned tool description.

By Laura Chen 4 days ago  |  Last Post: 4 days ago

Forum News and Vulnerability Disclosures
Has anyone done a proper side-channel analysis on the inference process within an agent loop?

By Oliver Stone 4 days ago  |  Last Post: 4 days ago

Forum Show and Tell
What's the best way to scope the boundary if the agent uses external APIs?

By Frank O'Brien 4 days ago  |  Last Post: 4 days ago

Forum FedRAMP and Government Deployments
How do I prove an agent didn't access a specific file or API endpoint?

By Connie Becker 7 days ago  |  Last Post: 4 days ago

Forum Agent Audit Log Design
Thoughts on using a separate security LLM to judge the safety of the primary agent's next action?

By Dmitri Volkov 6 days ago  |  Last Post: 4 days ago

Forum Indirect Injection via Tools and Retrieved Data
Is it safe to block all *.amazonaws.com except my S3 model bucket?

By Hal Newb 4 days ago  |  Last Post: 4 days ago

Forum Allowlist Design for Agent Network Access
As a dev new to security, what's the one thing I should not skip?

By Ella Morozov 1 week ago  |  Last Post: 4 days ago

Forum News and Vulnerability Disclosures
TIL: You can fingerprint agent sessions without user IDs. Here's how.

By Carlos Mendez 1 week ago  |  Last Post: 4 days ago

Forum Agent Audit Log Design
Is it safe to ignore the 'configuration needed' flag in my use case?

By anomaly_watcher 6 days ago  |  Last Post: 4 days ago

Forum Enclave Attestation and Verification
TIL: Some injection attempts leave a trace in the token probability distributions. Hard to use.

By Tina G. 4 days ago  |  Last Post: 4 days ago

Forum Injection Detection and Runtime Monitoring
Page 29 / 131

 

 

 

Share:
Share
Tweet
Share