Skip to content

Submission: AgentBusters - therapytrap#23

Open
huixu11 wants to merge 2 commits intoLambdaLabsML:mainfrom
huixu11:submission/AgentBusters/therapytrap
Open

Submission: AgentBusters - therapytrap#23
huixu11 wants to merge 2 commits intoLambdaLabsML:mainfrom
huixu11:submission/AgentBusters/therapytrap

Conversation

@huixu11
Copy link

@huixu11 huixu11 commented Jan 15, 2026

Demo Video

https://youtu.be/D991loZgFS4

Name Category Self-Designed Attack Succeeded Baseline Passed Relation to Lambda Scenarios
TherapyTrap Direct Logic Override (Jailbreak) ❌ No ✅ Yes (Round 2) ✅ Yes Based on Lambda TherapyTrap; addresses real-world AI mental health safety concerns

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant