openclaw-model-switch-2@0.1.3
CAUTION· static onlyPublisher claims: "OpenClaw AI 模型切换技能 - 用自然语言切换和添加 AI 模型。 支持 9+ 预置提供商(Gemini/GPT/Claude/Qwen/Kimi 等),智能判断模型特性,一键配置 API Key。 自动备份配置,安全重启网关。 关键词:openclaw, model, switch, ai, mult..." Observed in sandbox: static analysis only — behavior not yet observed.
Coverage
Static only; nothing was run yet.The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.
Is [email protected] safe to install?
KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-20 and scored it 59/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: OS command execution function call detected. Summary: static analysis only — behavior not yet observed.
Behavior trace
Queued for honeypot run · static analysis onlyThis version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.
Static findings
- **权限:** 取决于文件权限(建议 `chmod 600`)Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.result = subprocess.run(['openclaw', 'gateway', 'status'],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.os.system('openclaw gateway restart > /dev/null 2>&1')Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.subprocess.run(['python3', str(switch_script), model_key])Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.chmod +x model-switch/scripts/*.pyFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.4. **权限控制:** 确保 openclaw.json 权限正确(`chmod 600`)Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.2. 设置文件权限:`chmod 600 ~/.openclaw/openclaw.json`Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.Cost to the agent
Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.
Known vulnerabilities
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.
What would make this Verified
21 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- OS command execution function call detected≈ +9 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- Unclaimed publisher≈ +8 on the totalClaim williamwg2025: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
- Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.