Skip to content

Forum

AI Assistant
Forums
Security Patterns a...
Prompt Injection De...
Benchmarks and Eval...
 
Notifications
Clear all

Benchmarks and Evaluation Methodologies

Evaluating how well a runtime or defense actually resists prompt injection — benchmarks, red-team methodologies, and how to design tests that are more honest than vendor demos.
RSS
Page 1 / 4

Unpopular opinion: Prompt injection benchmarks should include a 'no defense' baseline

Last post by Em Supply, 9 hours ago

Posts: 2
Views: 4


Am I the only one who thinks OpenClaw's default skill permissions are too lax?

Last post by Dave Chen, 11 hours ago

Posts: 5
Views: 3


Anyone else finding that LangGraph's memory persistence doesn't honor least-privilege?

Last post by Quinn Morse, 1 day ago

Posts: 1
Views: 4


Claude Code vs Aider — which sandbox is easier to red-team with custom tools?

Last post by Pete O., 4 days ago

Posts: 12
Views: 49


Complete newbie here — what's a realistic first benchmark to run against OpenClaw?

Last post by Mike O'Brien, 5 days ago

Posts: 5
Views: 3


Guide: Reproducing the latest prompt injection research on OpenClaw in 30 minutes

Last post by Tom L., 5 days ago

Posts: 34
Views: 8


How do I apply threat modeling from the OWASP LLM Top 10 to OpenClaw?

Last post by Tina G., 5 days ago

Posts: 26
Views: 3


Just built a red-team dashboard that runs injection campaigns on all my Claw instances

Last post by David Stone, 5 days ago

Posts: 30
Views: 5


Complete newbie here — do I need to understand supply chain attacks before picking an agent runtime?

Last post by Kenji Tanaka, 7 days ago

Posts: 13
Views: 1


Did you see the CVE for a critical credential disclosure in LangGraph's default persistence?

Last post by Anna Vikström, 1 week ago

Posts: 12
Views: 2


Page 1 / 4
Share:
Share
Tweet
Share