agentscan-cli is a local, zero-dependency command-line tool that performs deterministic security scanning of AI agent skills and provides trusted distribution capabilities. It analyzes without executing code, delivering factual reports rather than subjective verdicts. Designed for developers working with LLM agents, MCP, and tools like Claude Code or Cursor, it is available on PyPI under the MIT license.
agentscan-cli sits in PulseGate's Developer Tools category. Securely auditing AI agent skills and dependencies without execution or third-party trust. agentscan-cli is an open-source project aimed at AI developers. agentscan-cli is open source under the MIT license. It runs on the command line, and it can be self-hosted.
It is developed by thesfb, and it first shipped in 2026. Development happens publicly on GitHub with 7 commits in the last 90 days. Among its 5 catalogued features are Security Scanning, AI Agent Analysis, and Zero Dependency. It exposes integrations via an MCP server.
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