🧰 PurpleLlama

The items that name it 3

• Chinese AI Model Writes More Hackable Code When Told It’s for US Contractor
  articleas classification.key entities2026-10-21
• Awesome LLM Security
  repoas tools2026-07-14

  set of tools to assess and improve LLM security

• Orca Security: AI Security Tools: How to Evaluate Them Across Every ML Attack Phase
  articleas tools2026-05-21It is written here as Purple Llama.

  LLM-specific safety via three components: Llama Guard (blocks risky/policy-violating content), Prompt Guard (prevents prompt injection, MITRE ATLAS AML.T0051), Code Shield (filters AI-generated code for security issues); released by Meta, December 2023; does not evaluate cloud infrastructure hosting

In every workspace you can read 5