Skip to content

jnMetaCode/shellward

v0.7.8 Breaking

This release includes 3 breaking changes for platform teams planning a safe upgrade.

Published 1mo MCP Security & Auth
✓ 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

Local client no longer uses browser folder upload, preventing massive uploads and fixing long‑path table corruption.

Full changelog

解决"上传 3 万个文件"和长路径压坏表格的问题。

变更

  • 本地客户端不再用浏览器文件夹上传（那会读取整个 node_modules，弹"上传 3 万+ 文件"，又慢又吓人）
  • 改为服务端目录浏览器：在网页里点进你本机的文件夹 → 服务端直接读取本机文件扫描，零上传、不出本机、自动跳过 node_modules
  • 公网模式禁止目录浏览（防扫服务器硬盘）
  • 配合跳过 release/*.app 构建产物 + 长路径换行修复，报告表格不再竖排乱码

试：npx [email protected] web --local → 点进文件夹 → 扫描当前文件夹。

全套 302 测试通过。

Breaking Changes

  • Removed browser‑based folder upload from the local client (previously read entire node_modules and uploaded >30k files).
  • Changed to server‑side directory browsing: web UI now triggers direct local file system scans with zero network transfer.
  • Public mode disables directory browsing to prevent disk scanning.
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.

Sign up free

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 →

Related context

Beta — feedback welcome: [email protected]