{"id":"purplellama","name":"Purple Llama","maker":"Meta","url":"https://github.com/meta-llama/PurpleLlama","repo":"meta-llama/PurpleLlama","summary":"A Meta project with open safety tools for generative AI, including Llama Guard, Prompt Guard, LlamaFirewall and CyberSecEval.","details":"Llama Guard classifies prompts and responses for safety, Prompt Guard detects prompt injection and jailbreak attempts, LlamaFirewall guards agents, CodeShield checks generated code, and CyberSecEval benchmarks cybersecurity risk. The repository as a whole is under the Llama community licence, while some components, such as LlamaFirewall and CodeShield, are MIT licensed.","open_source":false,"hosted":false,"verified":"2026-11-15","category":"safety","category_name":"Guardrails and security","page":"https://modelmoot.com/tools/purplellama","reviewed":"2026-11-15","checked":{"at":"2026-11-15T16:10:15.342Z","address_answers":true},"note":"Descriptions are the site's own. Facts under \"checked\" were read automatically from the tool's address and public repository."}