@hawon/nexus
hawonb711-tech esm
Local-first trust layer for AI coding agents — structural prompt-injection and action guards, secret scanning, semantic memory, and code review. No model API required.
Version 0.7.4 License MIT
Keywords
agent-firewallprompt-injectionai-agentagent-securityllm-securityai-securitysecret-scanningmcpclaude-codecursorcode-reviewsemantic-searchlocal-firstdeveloper-toolson-device
INSTALL
Top version - 0
Full @hawon/nexus Download Stats 
ShareKeywords
agent-firewall
prompt-injection
ai-agent
agent-security
llm-security
ai-security
secret-scanning
mcp
claude-code
cursor
code-review
semantic-search
local-first
developer-tools
on-device
Get a badge for your package
