⚡

AI Skill Store

AI Agent Skill Marketplace
← Back to Skills

health-claim-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 health-claim-guard.skill   "https://aiskillstore.io/v1/agent/skills/f048484b-92db-449e-9d8d-0aea035eaaae/download?platform=ClaudeCode"
▸ MCP tool call (after registering Skill Store MCP)
{
  "tool": "download_skill",
  "arguments": {
    "skill_id": "f048484b-92db-449e-9d8d-0aea035eaaae",
    "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

健康宣称合规扫描 — 保健品/食品宣传文案扫违规疗效宣称（根治/治愈/无副作用等），缺警示语即 FAIL（零依赖） 适用场景：当需要健康宣称合规扫描能力时使用本技能；触发词：health-claim-guard。

# health-claim-guard # AI 治理

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) 656f455392ae14de4401e7632d65a598333db645e6255735cf0ec33a7744ce1e

⚡ AGENT INFO USK v3

Capabilities
cli_tool
Permissions
✗ network
✗ filesystem
✗ subprocess
Interface
type: cli   entry_point: scripts/health_claim_guard.py   runtime: python3   call_pattern: args
Agent API
# 스킬 스키마 조회 (에이전트가 호출 방법을 파악) GET /v1/agent/skills/f048484b-92db-449e-9d8d-0aea035eaaae/schema # 플랫폼별 자동 변환 다운로드 GET /v1/agent/skills/f048484b-92db-449e-9d8d-0aea035eaaae/download?platform=OpenClaw GET /v1/agent/skills/f048484b-92db-449e-9d8d-0aea035eaaae/download?platform=ClaudeCode GET /v1/agent/skills/f048484b-92db-449e-9d8d-0aea035eaaae/download?platform=ClaudeCodeAgentSkill GET /v1/agent/skills/f048484b-92db-449e-9d8d-0aea035eaaae/download?platform=Cursor GET /v1/agent/skills/f048484b-92db-449e-9d8d-0aea035eaaae/download?platform=GeminiCLI GET /v1/agent/skills/f048484b-92db-449e-9d8d-0aea035eaaae/download?platform=CodexCLI GET /v1/agent/skills/f048484b-92db-449e-9d8d-0aea035eaaae/download?platform=CustomAgent

Installation

1
Install the skill using openclaw_skill_manager.py.
python openclaw_skill_manager.py --install health-claim-guard
2
Verify installation
python openclaw_skill_manager.py --list-installed
3
Install a specific version (optional)
python openclaw_skill_manager.py --install health-claim-guard --version 1.0.0
1
Download the skill package.
curl -O https://aiskillstore.io/v1/skills/f048484b-92db-449e-9d8d-0aea035eaaae/download
2
Place it in the Claude Code commands directory.
unzip health-claim-guard.skill -d ~/.claude/commands/health-claim-guard/
3
Use it as a slash command in Claude Code.
/health-claim-guard
1
Download the Agent Skills package.
curl -O https://aiskillstore.io/v1/agent/skills/f048484b-92db-449e-9d8d-0aea035eaaae/download?platform=ClaudeCodeAgentSkill
2
Unzip it into the Claude Code skills directory.
unzip health-claim-guard-agent-skill-*.skill -d ~/.claude/skills/health-claim-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/f048484b-92db-449e-9d8d-0aea035eaaae/download?platform=Cursor
2
Unzip and place it in a permanent location.
unzip health-claim-guard-cursor-*.skill -d ~/.cursor/skills/health-claim-guard/
3
Add the MCP server config to .cursor/mcp.json, then restart Cursor.
cat ~/.cursor/skills/health-claim-guard/cursor_mcp_config.json
1
Download the Gemini CLI-converted package.
curl -O https://aiskillstore.io/v1/agent/skills/f048484b-92db-449e-9d8d-0aea035eaaae/download?platform=GeminiCLI
2
Unzip and place it in a permanent location.
unzip health-claim-guard-geminicli-*.skill -d ~/.gemini/skills/health-claim-guard/
3
Add the MCP server config to ~/.gemini/settings.json, then restart Gemini CLI.
cat ~/.gemini/skills/health-claim-guard/gemini_settings_snippet.json
1
Download the Codex CLI-converted package.
curl -O https://aiskillstore.io/v1/agent/skills/f048484b-92db-449e-9d8d-0aea035eaaae/download?platform=CodexCLI
2
Unzip and place it in a permanent location.
unzip health-claim-guard-codexcli-*.skill -d ~/.codex/skills/health-claim-guard/
3
Add the MCP server config to ~/.codex/config.toml, then restart Codex CLI.
cat ~/.codex/skills/health-claim-guard/codex_config_snippet.toml
1
Download the skill package via REST API.
GET https://aiskillstore.io/v1/skills/f048484b-92db-449e-9d8d-0aea035eaaae/download
2
Place it in your agent platform's skills directory.
cp health-claim-guard.skill ./skills/
3
Fetch platform-specific details via the Install Guide API.
GET https://aiskillstore.io/v1/skills/f048484b-92db-449e-9d8d-0aea035eaaae/install-guide?platform=CustomAgent

Requirements

Security Vetting Report

Vetting Result CAUTION

Findings: ["메타데이터 경고: 권장 필드 없음: 'platform_compatibility' (SKILL.md v2 권장)", "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 건강 관련 문구의 규정 준수 여부를 검사하는 안전하고 독립적인 스킬입니다.

Issues Found

  • 메타데이터의 `allowed-tools` 필드와 `permissions` 필드 간의 불일치: `allowed-tools`는 'Read, Glob, Grep, Bash, Write, WebFetch'를 선언하지만, `permissions`는 'network: false, filesystem: false, subprocess: false'로 선언되어 실제 코드의 동작과 일치합니다. 이는 메타데이터의 일관성 문제로, 현재 코드의 보안 위험은 아닙니다.
Reasoning

제공된 Python 코드는 `argparse`, `json`, `sys`와 같은 표준 라이브러리만 사용하며, 외부 네트워크 통신, 파일 시스템 접근 또는 서브프로세스 실행을 수행하지 않습니다. 이는 메타데이터의 `permissions` 필드(`network: false`, `filesystem: false`, `subprocess: false`)와 완벽하게 일치합니다. 코드는 난독화되어 있지 않으며, 악의적인 목적(데이터 탈취, 시스템 파괴 등)을 가진 어떠한 패턴도 발견되지 않았습니다. 스킬의 기능은 입력된 텍스트를 기반으로 건강 관련 문구의 규정 준수 여부를 검사하는 것으로, 코드의 품질과 목적이 일치합니다. 메타데이터의 `allowed-tools` 필드는 'Read, Glob, Grep, Bash, Write, WebFetch'를 포함하고 있으나, 실제 코드에서는 이러한 도구들을 사용하지 않으며, `permissions` 필드가 더 제한적으로 선언되어 있어 현재 버전의 스킬은 안전하다고 판단됩니다. `risk_tier`가 'medium'으로 선언되었지만, 실제 코드의 동작은 'low' 위험 수준에 해당합니다.

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