domains / families / security / nyx-archive-skill-security-protocol

nyx-archive-skill-security-protocol

separate

Teach your AI agent to think about security. A reasoning methodology for vetting skills before installation — red/green flag heuristics, 4-phase audit protocol, post-install verification. No scripts, no dependencies. Just judgment. Built on fallibilism (being wrong about a skill's safety is recoverable; being overconfident is not) and relational security (you and your human decide together on edge cases — trust is built through transparency, not just detection).

When to use

• vetting skills before installation
• 4-phase security audit
• red/green flag check
• post-installation verification
• explaining security reasoning

When not to use

• scanning for threats
• running scripts
• using dependencies

Skill page

Source