Jailbreak Detection
2 items across the graph — tagged with Jailbreak Detection.
From the graph · 2
repo
killertcell428/aigis
→repoDeterministic, zero-dependency Python firewall for AI agents — MCP rug-pull, memory poisoning, indirect injection, exfil channels. 44 compliance templates (US/C…
hermes-labs-ai/little-canary
→Detects prompt injection by its effect on a sacrificial canary model, not just pattern matching: untrusted input hits a powerless model first, a behavioral chec…