simple818/ai-agent-permission-probe

Description and use

Read only AI Agent permission boundary probe — evidence backed permission matrix, risk ratings, bilingual Skill EN/中文 , three format reports, visual HTML with term explanations and optional fix center.

Compatible agents

• Claude Code
• Hermes
• Codex CLI

Limitations and review notes

GitHub-discovered skill metadata only; install commands are not executed by AtlasRepo.