dsh破甲 核心精简版(DSH NEXT / rc.4 专用;独立包名、模块 id、状态目录)
-
Updated
Nov 9, 2026 - JavaScript
dsh破甲 核心精简版(DSH NEXT / rc.4 专用;独立包名、模块 id、状态目录)
Harness security for AI agents, for SQL databases: a Lock of the Lock Family. PII-masked queries; connections and writes approved in lox run (CLI + MCP).
Secure Harness AI — the security control plane for production AI agents. SHAI sits between your agent and everything it can touch: tools, external APIs, files, and users. It enforces security at the boundaries — not by hoping the model behaves, but by intercepting every action before it executes.
Your AI agent works on your production database without holding the password. Harness security for AI agents: personal data comes back masked, and a write waits for your approval, outside the agent.
Harness security for AI agents, for files: a Lock of the Lock Family. Agents ask yes/no questions about files (S3, SFTP, disk) they never read.
Harness security for AI agents, for SSH: a Lock of the Lock Family. Let your AI agent run commands on your servers without ever handing it the SSH key.
Harness security for AI agents, for RabbitMQ: a Lock of the Lock Family. Masked queue inspection; message reads and actions approved in lox run (CLI + MCP).
Harness security for AI agents: the shared core of the Lock Family (console, policies, masking, signed hub tickets, audit, MCP wiring).
Your AI reads the logs, not the people in them. Masked, bounded log search for AI agents (MCP), with a human-held console.
Harness security for AI agents, for outbound HTTP(S): a Lock of the Lock Family. An egress gate with approvals in lox run and proxy-side credential injection.
Harness security for AI agents: the Lock Family's approval hub and its lox CLI. lox run approves outside the agent's harness, signs decisions, never sees values in clear.
To associate your repository with the harness-security topic, visit your repo's landing page and select "manage topics."