Agent Skills
› EverClaw/EverClaw
› skillguard
skillguard
GitHub用于扫描Agent技能包的安全工具，检测凭证窃取、代码注入等风险。支持区分内外源信任模型，提供多种扫描命令与安全评分，确保安装前评估潜在威胁。
触发场景
检查技能包安全性
审计外部下载的技能
检测提示词注入
扫描本地或ClawHub技能
安装
npx skills add EverClaw/EverClaw --skill skillguard -g -y
SKILL.md
Frontmatter
{
"name": "skillguard",
"metadata": {
"openclaw": {
"requires": {
"bins": [
"node"
]
}
}
},
"description": "Security scanner for AgentSkill packages. Scan skills for credential theft, code injection, prompt manipulation, data exfiltration, and evasion techniques before installing them. Use when evaluating skills from ClawHub or any untrusted source."
}
SkillGuard — Agent Security Scanner
When asked to check, audit, or scan a skill for security, use SkillGuard.
Trust Model (v0.3)
SkillGuard distinguishes between internal (trusted) and external (untrusted) skills:
- Internal skills — Skills under
~/.openclaw/workspace/skills/or~/.openclaw/workspace/claw-repos/. These are skills we authored ourselves. - External skills — Everything else (ClawHub downloads, third-party packages, etc.)
Why it matters
Internal skills legitimately use patterns like exec(), process.env.API_KEY, fetch(), and writeFile() — that's infrastructure code doing its job. Flagging those as "suspicious" creates noise that buries real issues.
For internal skills, SkillGuard uses vulnerability-focused scanning:
- ✅ Still flags: hardcoded secrets, reverse shells, pickle deserialization, unsafe YAML, actual code obfuscation, prompt injection in operational code
- ❌ Suppresses: "uses exec", "reads env vars", "makes HTTP requests", "writes files", "references private keys" (in wallet tools), "uses sudo" (in setup scripts), behavioral compound signatures
For external skills, full paranoid threat-model scanning applies — every pattern is treated as potentially malicious.
Overriding trust
Use --untrusted to force external mode on an internal skill:
node src/cli.js scan /path/to/skill --untrusted
Commands
Scan a local skill directory
node /home/claw/.openclaw/workspace/skillguard/src/cli.js scan <path>
Scan with compact output (for chat)
node /home/claw/.openclaw/workspace/skillguard/src/cli.js scan <path> --compact
Check text for prompt injection
node /home/claw/.openclaw/workspace/skillguard/src/cli.js check "<text>"
Batch scan multiple skills
node /home/claw/.openclaw/workspace/skillguard/src/cli.js batch <directory>
Scan a ClawHub skill by slug
node /home/claw/.openclaw/workspace/skillguard/src/cli.js scan-hub <slug>
Score Interpretation
- 80-100 ✅ LOW risk — safe to install
- 50-79 ⚠️ MEDIUM — review findings before installing
- 20-49 🟠 HIGH — significant security concerns
- 0-19 🔴 CRITICAL — do NOT install without manual review
Output Formats
- Default: full text report
--compact: chat-friendly summary--json: machine-readable full report--quiet: score and verdict only
版本历史
- f580bc4 当前 2026-07-25 11:17
