by 安全扫描
OpenClaw
安全
high confidence该技能仅提供指令，无需安装、凭证或特殊指令，其声明目的与实际行为一致。
评估建议
该技能内部一致性强，风险低，因为它仅提供指令且不请求凭证。然而：(1) SKILL.md 信息简短——如果需要可复制/验证结果，请向作者请求示例/测试或计算方法描述；(2) 除非信任其实现和隐私实践，否则避免向任何角色提供敏感个人或财务数据；(3) SKILL.md 列出价格（$9.90）——安装前请在平台上确认计费条款。如果您想要更强的保证，请从开发者请求一个工作示例或可解释的算法。...详细分析 ▾
✓ 用途与能力
The name/description (risk-reward calculation / actuary persona) align with the SKILL.md content (persona, tuning parameters). There are no unrelated required binaries, env vars, or config paths.
ℹ 指令范围
SKILL.md is very short and mostly defines a persona and a few configuration parameters (response_delay, speech_speed, caution_coefficient, risk_reminder). It does not instruct the agent to read files, access credentials, or call external endpoints, but it is also vague about how calculations are performed — that grants the agent broad discretion in behavior (normal for a persona skill but worth noting).
✓ 安装机制
No install spec or code files are present — this is instruction-only, which minimizes risk because nothing is written to disk or downloaded by the skill itself.
✓ 凭证需求
No environment variables, credentials, or config paths are requested. The skill does not ask for secrets or unrelated service tokens.
✓ 持久化与权限
always is false and model invocation is allowed (the platform default). The skill does not request persistent or elevated privileges or modify other skills.
安全有层次，运行前请审查代码。
运行时依赖
无特殊依赖
版本
latestv3.0.02026/3/19
此版本无变化检测。
● 无害
安装命令
点击复制官方npx clawhub@latest install psyvector-pv25
镜像加速npx clawhub@latest install psyvector-pv25 --registry https://cn.longxiaskill.com镜像同步中