{"id":"promptmap","name":"promptmap","maker":"Utku Sen","url":"https://github.com/utkusen/promptmap","repo":"utkusen/promptmap","summary":"A command-line scanner that tests LLM applications for prompt injection, in white-box or black-box mode.","details":"In white-box mode it runs a target model with the given system prompt; in black-box mode it sends attack prompts to an HTTP endpoint. A second model judges whether each attack succeeded. It is written in Python and released under GPL 3.0.","open_source":true,"hosted":false,"verified":"2026-11-15","category":"safety","category_name":"Guardrails and security","page":"https://modelmoot.com/tools/promptmap","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."}