jnMetaCode/shellward

v0.5.10 Feature

This release adds 2 notable features for engineering teams evaluating rollout.

Published 2mo MCP Security & Auth

View tool

✓ No known CVEs patched

Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

agent-security ai-agent ai-firewall ai-safety ai-security claude-code

+14 more

cursor data-exfiltration dlp guardrails hermes-agent langchain llm-security mcp mcp-security openclaw pii-detection prompt-injection security shellward

Summary

AI summary

Expanded npm keywords and added competitor comparison table in README.

Full changelog

What's New

README

Added competitor comparison table (vs agentguard, pipelock, Sage, AgentSeal)
Both English and Chinese sections updated
arXiv:2603.08665 reference (GenAI discovering 38 vulnerabilities in 7 hours)

npm Search Visibility

Keywords expanded from 18 to 29 (added mcp-security, claude-code, ai-firewall, etc.)
Description optimized for search engines

Previous (v0.5.9)

mail/sendmail/mutt commands now detected in data exfiltration patterns
L5 Security Gate includes DLP data flow check
32 injection rules (18 ZH + 14 EN)
i18n: all user-facing strings are locale-aware

Install

npm install shellward
# or
openclaw plugins install shellward

View diff on GitHub

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.

Share this release

Share on X Share on Bluesky

Track jnMetaCode/shellward

Get notified when new releases ship.

About jnMetaCode/shellward

AI 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.

All releases →