agent-smith

Open-source AI pentest framework — 50+ tools and chained skills for authorized security testers.

Pluginfreeglobal

agent-smith is an open-source AI pentest framework that gives an LLM 50+ tools and chainable skill modules — such as web exploitation and AI red-teaming — so it can plan and execute authorized security tests while the human tester directs scope and judgment, producing end-to-end deliverables including proof-of-concepts. It explicitly restricts use to systems the tester owns or has written permission to test, and supports Claude Code, OpenAI Codex, OpenCode, or fully local and offline models.

Website

Full match profile

Behind the summary, Matchbox keeps a richer profile of agent-smith - the signals our matcher actually reads to decide when to surface it. It stays private; claim the listing to see and control it.

Problem & pain-point mapping
Who we surface it to (audience fit)
What it's a strong alternative to
Trust & credibility signals

Claim agent-smith to unlock →

Try Matchbox with your own problem

Describe what is not working - we’ll show you whether agent-smith (or something else) actually fits.

Try a problem