hugoii/llm-agent-audit

Trace-backed Agent Authorization Reviews for tool-using AI agents. Staging-only evidence for payment, record-change, access, and export actions.

2 best points · 0 comments · 1 Hacker News post · 62 GitHub stars · View on GitHub

Hacker News discussions

• Model choice is not an authorization layer (2 points, 0 comments, by hugoii, 2026-06-11)