Skip to content

Releases: jnMetaCode/shellward

v0.4.0 — Hook Error Handling, Update Notifications, Remote Vuln DB

12 Mar 14:41

Choose a tag to compare

What's New

Hook Error Handling (Fail-Safe)

  • createSafeApi() wrapper: all 8 defense layers get automatic try-catch
  • before_tool_call errors → block (deny on error, safer than allow)
  • Other hook errors → pass-through (don't break the chain)
  • All errors logged at CRITICAL level

Non-Blocking Update Notifications

  • Checks npm registry for new versions (24h interval)
  • Notification dedup: same version only notified once — won't repeat after user has seen it
  • Silent on network failure, cached to avoid repeated timeouts

Remote Vulnerability Database

  • 17 real CVEs/GHSAs from NVD and GitHub Security Advisories
  • 1 supply chain alert (SANDWORM_MODE campaign)
  • 24h cache, graceful fallback to local built-in DB
  • /check-updates command shows vuln DB source and details

Security Fixes

  • ReDoS fix: email regex 333x speedup on large text (14s → 43ms on 200KB)
  • Injection rule gaps: expanded Chinese rules, added cross-language injection detection (26 total rules)
  • Fork bomb regex: fixed pattern broken by command splitting
  • Defensive input handling: non-string toolName/params no longer crash
  • Regex state pollution: fixed global flag leak in /scan-plugins

Testing

  • 100 tests across 3 suites (37 integration + 42 edge cases + 21 update check)
  • Performance: 125,000 tool checks/sec, 200KB PII scan in 55ms

Install: openclaw plugins install shellward

ShellWard v0.3.4 — First Bilingual AI Agent Security

12 Mar 10:09

Choose a tag to compare

ShellWard v0.3.4

First bilingual (EN/ZH) security plugin for OpenClaw — the only plugin with Chinese prompt injection detection & Chinese PII redaction.

Install

npm install shellward

Or one-click:

curl -fsSL https://raw.githubusercontent.com/jnMetaCode/shellward/main/install.sh | bash

8 Defense Layers

Layer What it does
L1 Prompt Guard Security rules + canary token injection
L2 Output Scanner PII/secret redaction (Chinese ID card, phone, bank card + global)
L3 Tool Blocker Dangerous command blocking (15 rules)
L4 Input Auditor Prompt injection detection (13 Chinese + 12 English rules)
L5 Security Gate Defense-in-depth pre-execution check
L6 Outbound Guard LLM response redaction + canary leak detection
L7 Data Flow Guard Data exfiltration chain detection
L8 Session Guard Session audit + subagent monitoring

Why ShellWard

  • Only bilingual plugin — Chinese + English injection detection
  • Chinese PII — ID card (checksum), phone, bank card (Luhn) — no other tool has this
  • Zero dependencies — Node.js built-in modules only
  • No build step — TypeScript loaded by OpenClaw's jiti
  • All channels — Telegram, Slack, Feishu, WhatsApp, Discord...
  • Dual modeenforce (block + log) or audit (log only)