⚡

AI Skill Store

AI Agent Skill Marketplace
← Back to Skills

tool-call-guard

v1.0.0 approved updated today
USK v3 ✅ Verified
⬇ Download
Install Guide↓
🤖 Agent install commands (curl / MCP / Claude Desktop)
▸ curl one-liner
curl -L -o tool-call-guard.skill   "https://aiskillstore.io/v1/agent/skills/0ed5588f-b070-4a9b-83e9-44c22a62b126/download?platform=ClaudeCode"
▸ MCP tool call (after registering Skill Store MCP)
{
  "tool": "download_skill",
  "arguments": {
    "skill_id": "0ed5588f-b070-4a9b-83e9-44c22a62b126",
    "platform": "ClaudeCode"
  }
}
▸ Claude Desktop / Cursor MCP config (one-time)
{
  "mcpServers": {
    "skill-store": {
      "url": "https://aiskillstore.io/mcp/"
    }
  }
}
📖 Full agent API guide: /llms.txt  ·  MCP server card

当用户说『agent乱调工具』『误删了文件』『不该发邮件却发了』『怎么给AI的工具加权限边界』，或在给 agent 接工具（文件/网络/数据库/消息/支付）想防危险动作时使用。把每次 tool call 当『需授权操作』：按 读/写/删/外发/支付 分级，危险动作先拦截+提示确认，低风险放行。理论根基：LGD 三律（有籍·有证·有门禁）。触发词：工具调用安全、agent权限、tool call guard、危险动作拦截、误删、误发、AI工具边界、function安全。

# 工具调用安全 # tool call guard # agent权限 # 危险动作拦截 # 最小权限 # AI安全 # 门禁

Basic Info

Owner 👤 Steven Zhao Category — Registered 2026-10-17 Last Updated 2026-10-17 Latest Version 1.0.0 Packaged At 2026-10-17 Vetting Status approved Downloads 0 Checksum (SHA256) e09f47c1fb8dbd3bb9882032f2c8aa25567f3441f2e8fa1e5777fd9f5f3d4431

⚡ AGENT INFO USK v3

Capabilities
tool-call guardrails security
Permissions
✗ network
✗ filesystem
✗ subprocess
Interface
type: cli   entry_point: scripts/tool_guard.py   runtime: python3   call_pattern: args
Agent API
# 스킬 스키마 조회 (에이전트가 호출 방법을 파악) GET /v1/agent/skills/0ed5588f-b070-4a9b-83e9-44c22a62b126/schema # 플랫폼별 자동 변환 다운로드 GET /v1/agent/skills/0ed5588f-b070-4a9b-83e9-44c22a62b126/download?platform=OpenClaw GET /v1/agent/skills/0ed5588f-b070-4a9b-83e9-44c22a62b126/download?platform=ClaudeCode GET /v1/agent/skills/0ed5588f-b070-4a9b-83e9-44c22a62b126/download?platform=ClaudeCodeAgentSkill GET /v1/agent/skills/0ed5588f-b070-4a9b-83e9-44c22a62b126/download?platform=Cursor GET /v1/agent/skills/0ed5588f-b070-4a9b-83e9-44c22a62b126/download?platform=GeminiCLI GET /v1/agent/skills/0ed5588f-b070-4a9b-83e9-44c22a62b126/download?platform=CodexCLI GET /v1/agent/skills/0ed5588f-b070-4a9b-83e9-44c22a62b126/download?platform=CustomAgent

Installation

Compatible Platforms windows macos linux

1
Install the skill using openclaw_skill_manager.py.
python openclaw_skill_manager.py --install tool-call-guard
2
Verify installation
python openclaw_skill_manager.py --list-installed
3
Install a specific version (optional)
python openclaw_skill_manager.py --install tool-call-guard --version 1.0.0
1
Download the skill package.
curl -O https://aiskillstore.io/v1/skills/0ed5588f-b070-4a9b-83e9-44c22a62b126/download
2
Place it in the Claude Code commands directory.
unzip tool-call-guard.skill -d ~/.claude/commands/tool-call-guard/
3
Use it as a slash command in Claude Code.
/tool-call-guard
1
Download the Agent Skills package.
curl -O https://aiskillstore.io/v1/agent/skills/0ed5588f-b070-4a9b-83e9-44c22a62b126/download?platform=ClaudeCodeAgentSkill
2
Unzip it into the Claude Code skills directory.
unzip tool-call-guard-agent-skill-*.skill -d ~/.claude/skills/tool-call-guard/
3
Restart Claude Code — the skill is auto-loaded at session start. No slash command needed.
1
Download the Cursor-converted package.
curl -O https://aiskillstore.io/v1/agent/skills/0ed5588f-b070-4a9b-83e9-44c22a62b126/download?platform=Cursor
2
Unzip and place it in a permanent location.
unzip tool-call-guard-cursor-*.skill -d ~/.cursor/skills/tool-call-guard/
3
Add the MCP server config to .cursor/mcp.json, then restart Cursor.
cat ~/.cursor/skills/tool-call-guard/cursor_mcp_config.json
1
Download the Gemini CLI-converted package.
curl -O https://aiskillstore.io/v1/agent/skills/0ed5588f-b070-4a9b-83e9-44c22a62b126/download?platform=GeminiCLI
2
Unzip and place it in a permanent location.
unzip tool-call-guard-geminicli-*.skill -d ~/.gemini/skills/tool-call-guard/
3
Add the MCP server config to ~/.gemini/settings.json, then restart Gemini CLI.
cat ~/.gemini/skills/tool-call-guard/gemini_settings_snippet.json
1
Download the Codex CLI-converted package.
curl -O https://aiskillstore.io/v1/agent/skills/0ed5588f-b070-4a9b-83e9-44c22a62b126/download?platform=CodexCLI
2
Unzip and place it in a permanent location.
unzip tool-call-guard-codexcli-*.skill -d ~/.codex/skills/tool-call-guard/
3
Add the MCP server config to ~/.codex/config.toml, then restart Codex CLI.
cat ~/.codex/skills/tool-call-guard/codex_config_snippet.toml
1
Download the skill package via REST API.
GET https://aiskillstore.io/v1/skills/0ed5588f-b070-4a9b-83e9-44c22a62b126/download
2
Place it in your agent platform's skills directory.
cp tool-call-guard.skill ./skills/
3
Fetch platform-specific details via the Install Guide API.
GET https://aiskillstore.io/v1/skills/0ed5588f-b070-4a9b-83e9-44c22a62b126/install-guide?platform=CustomAgent

Requirements

Security Vetting Report

Vetting Result CAUTION

Findings: ["USK v3 경고: input_schema.type이 'object'가 아닙니다", "USK v3 경고: output_schema.type이 'object'가 아닙니다", 'USK v3 경고: 이 스킬은 자동 변환 조건을 충족하지 않아 manual_install로 처리됩니다']

✅ No security risks found.

AI Review Stage

Reviewer gemini Risk Level 🟢 Low Review Summary AI 에이전트의 위험한 도구 호출을 분석하고 차단/확인/허용을 결정하는 보안 가드레일 스킬입니다. 선언된 권한을 준수하며 악의적인 코드가 없습니다.

Issues Found

  • AI 응답이 토큰 한도로 잘렸으나 verdict 추출 성공
Reasoning

{ "verdict": "approved", "risk_level": "low", "summary": "AI 에이전트의 위험한 도구 호출을 분석하고 차단/확인/허용을 결정하는 보안 가드레일 스킬입니다. 선언된 권한을 준수하며 악의적인 코드가 없습니다.", "issues": [], "reasoning": "제공된 스킬 메타데이터와 코드(`scripts/tool_guard.py`)를 분석한 결과, 다음과 같은 판단을 내렸습니다.\n\n1. **선언된 permissions(network/filesystem/subprocess)과 실제 코드가 일치하는가?**\n * 메타데이터는 `network: false`, `filesystem: false`, `subprocess: false`로 선언되어 있습니다.\n * 코드(`tool_guard.py`)는 `argparse`, `json`, `pathlib`, `re` 등 표준 라이브러리 모듈만 사용하며, 네트워

Version History

Version USK v3 Vetting Status Packaged At Downloads Changelog
v1.0.0 ✓ approved 2026-10-17 ⬇ 0 1.0.0: initial upload (USK v3)

Reviews & Ratings

No reviews yet. Be the first to leave one!

✍️ Write a Review