rudratoshs/buried-injections
🛡️ Regex catches 0%, Meta's Prompt Guard 2 catches 1% of 629 realistic AgentDojo injection attacks when they're buried in tool output. Reproducible benchmark.
GitHub repository with 13 stars and 1 forks.
Language: Python
Topics: agentdojo, ai-agents, benchmark, llm-security, mcp, prompt-guard, prompt-injection