← 返回 Skills 市场
143
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install trustskills
功能描述
Use this skill when a user wants a trust decision before installing from a skill URL, marketplace, or GitHub repo. It checks a compact allowlist of trusted d...
安全使用建议
This skill is a lightweight URL/org allowlist checker — it only looks at the source URL and matches it to a small set of trusted roots. It does NOT do code or signature verification, ownership proof, or malware analysis. It's safe to invoke (no creds, no install), but do not rely on it alone for high-risk installations: manually verify the repository owner, check upstream vendor docs, inspect code or release artifacts, look for signed releases or SBOMs, and prefer vendor-owned GitHub orgs or official marketplace entries when possible. Note the compact allowlist contains narrow exceptions (e.g., a specific ClawHub publisher); treat such rules as policy shortcuts rather than technical guarantees and follow up with manual checks when the install would affect sensitive systems.
功能分析
Type: OpenClaw Skill
Name: trustskills
Version: 0.1.0
The 'trustskills' bundle is a prompt-based skill designed to help users verify the provenance of other AI skills using a hardcoded allowlist of trusted vendors (e.g., OpenAI, Anthropic, Google). It contains no executable code, requests no sensitive permissions, and its instructions in SKILL.md focus on providing restrictive, safety-oriented trust decisions without performing any background data exfiltration or unauthorized execution.
能力评估
Purpose & Capability
Name, description, and SKILL.md all describe a compact allowlist-based trust check. There are no unrelated environment variables, binaries, or install steps requested — the declared purpose aligns with what the skill asks for.
Instruction Scope
Instructions restrict behavior to parsing a provided URL and matching it against an explicit trusted-roots list, returning a short verdict. This is coherent, but the workflow is purely syntactic (URL/org matching) and intentionally does not perform deep verification (signatures, SBOMs, or repo-level ownership verification). Relying solely on this output for high-risk installs would be insufficient.
Install Mechanism
No install spec and no code files — instruction-only skill. Nothing will be written to disk or executed beyond the agent following the prose instructions.
Credentials
The skill requires no environment variables, credentials, or config paths. The minimal privilege footprint matches the stated purpose.
Persistence & Privilege
always is false and the skill does not request persistent system presence or modify other skills. Autonomous invocation is allowed (platform default) but not combined with elevated privileges.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install trustskills - 安装完成后，直接呼叫该 Skill 的名称或使用
/trustskills触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v0.1.0
trustskills 0.1.0 – Initial release
- Provides a trust decision for skill sources before installation by checking a compact allowlist of official distribution channels.
- Distinguishes between vendor-owned repos, official directories/marketplaces, and unverified third-party sources.
- Responds with a clear verdict: Trusted, Not trusted, or Trust the index but not automatically the item.
- Does not perform code or malware analysis; focuses strictly on source provenance.
- Excludes skill functionality explanations unless explicitly requested.
元数据
常见问题
TrustSkills 是什么？
Use this skill when a user wants a trust decision before installing from a skill URL, marketplace, or GitHub repo. It checks a compact allowlist of trusted d... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 143 次。
如何安装 TrustSkills？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install trustskills」即可一键安装，无需额外配置。
TrustSkills 是免费的吗？
是的，TrustSkills 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
TrustSkills 支持哪些平台？
TrustSkills 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 TrustSkills？
由 K（@likw99）开发并维护，当前版本 v0.1.0。
推荐 Skills