agentaudit-scanner is an open-source CLI tool that scans AI agent skills, rule files, and MCP configurations for security risks like prompt injections and hidden instructions. It is designed for AI security engineers and developers to ensure safe agent deployments.
agentaudit-scanner sits in PulseGate's LLM eval & observability category. It focuses on detecting security vulnerabilities such as prompt injections and dangerous permissions in AI agent configurations before deployment. It is built as an open-source project for AI security engineers and agent developers. agentaudit-scanner is open source under the MIT license. It runs on the command line.
It is developed by sudan94, and it first shipped in 2026. Development happens publicly on GitHub with 2 commits in the last 90 days. Key capabilities include security scanning, prompt injection detection, and rule file analysis.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do