Prompt injection scanner CLI - substring, unicode, secrets, and ML detection
parry-guard is a LLM eval & observability product. It focuses on detecting and preventing prompt injection vulnerabilities in AI and LLM applications. parry-guard is an open-source project aimed at security engineers. The project is open source (MIT). It runs on the web and the command line.
It is developed by vaporif, and the product first shipped in 2026. The project is developed in the open on GitHub with 44 stars and 40 commits in the last 90 days. Across PulseGate's embedding index, parry-guard has few near neighbours, marking it as relatively distinct. Among its 5 catalogued features are prompt injection scanning, unicode detection, and secrets detection.
Latest indexed changes and source events
Other apps tracked under the same category.
