agent-redteam

SKILLWorkflowcommunity
v0.0.0HefrockMITUpdated 14d agoSource →

Generates adversarial test cases targeting safe-failure behavior — refusals, hedging, graceful degradation. Use this when you want to stress-test an agent's safety boundaries, check for prompt injection, or build an adversarial eval set. Pairs with agent-eval for scoring: agent-redteam generates cas

Community-submitted skill. Not yet reviewed by the Forge team. Full prompt content may not be available.Request review →
1Clients
1Formats
14d agoLast update
Skill
AuthorHefrock
Version0.0.0
LicenseMIT
CategoryWorkflow
Formatsskill.md
PromptNot published
Compatibility
Claude✓ Supported
Cursor
Copilot
ChatGPT
Gemini
About

Generates adversarial test cases targeting safe-failure behavior — refusals, hedging, graceful degradation. Use this when you want to stress-test an agent's safety boundaries, check for prompt injection, or build an adversarial eval set. Pairs with agent-eval for scoring: agent-redteam generates cases, agent-eval runs and scores them. Triggers on "red team my agent," "test for jailbreaks," "advers

Keywords
skillclaude