jnMetaCode/shellward
MCP Security & AuthAI Agent Security Middleware & MCP Server with 8-layer defense including prompt injection detection, DLP data flow tracking, command blocking, and PII detection. 7 MCP tools, zero dependencies.
Features
- 8 defense layers: prompt guard, input auditor, tool blocker, output scanner, security gate, outbound guard, data flow guard, session guard
- Chinese‑language PII detection (ID card, phone numbers, credit cards, API keys) with zero false positives focus
- Real‑time blocking of data exfiltration chains and prompt injection in AI agents
Recent releases
View all 40 releases →Weekly OSS security release digest.
The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.
No spam, unsubscribe anytime.
About
Stars
123
Forks
22
Languages
TypeScript
JavaScript
Shell
Downloads/week
84
↓40%
NPM Maintainers
1
Single npm maintainer
Contributors
2
TypeScript
Types included ✓
Install & Platforms
Install via
npm
