← 返回 Skills 市场
saqierma-cyber

Super Agent Skills

作者 Saqierma.a · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
316
总下载
0
收藏
1
当前安装
1
版本数
在 OpenClaw 中安装
/install super-agent-skills
功能描述
Comprehensive AI Agent capability library covering 20+ essential skills from file ops to cloud services, security, monitoring, and CI/CD.
安全使用建议
This skill is inconsistent: it claims extensive cloud/security/ops abilities but does not declare the tools or credentials it would need and instructs running shell and network commands that can read or send local data. If you consider using it: (1) do not enable it in production or as an always-on autonomous skill; (2) run it only in a fully isolated test environment or container; (3) require explicit user confirmation before any shell/net calls; (4) ask the author for provenance, a list of required binaries and exact env vars, and a clear threat model; (5) prefer skills from known sources or with a code base you can review. If you cannot verify what credentials it expects or why, do not install or allow autonomous use.
功能分析
Type: OpenClaw Skill Name: super-agent-skills Version: 1.0.0 The skill bundle provides an AI agent with a broad range of high-privilege capabilities, including network access (curl/wget), container management (Docker/Kubernetes), and task scheduling (cron/at). A 'Quick Environment Check' section in SKILL.md instructs the agent to perform system reconnaissance (uname -a, tool discovery), which is a common precursor to exploitation. While these tools are presented as general capabilities, the lack of a specific, narrow use case and the inclusion of environment fingerprinting commands warrant a suspicious classification.
能力评估
Purpose & Capability
The skill advertises 20+ capabilities (cloud, CI/CD, security scanning, databases, containers) that legitimately require system tools and cloud credentials, yet the registry metadata lists no required binaries, no required environment variables, and no primary credential. This mismatch is inconsistent: either the skill is only documentation or it expects access it did not declare.
Instruction Scope
SKILL.md instructs the agent to run commands that read local files (ls ~/skills/), probe system state (which, uname -a), schedule jobs (at/cron), execute network calls (curl examples), and run container/orchestration commands (docker, kubectl). Those are broad actions that can access or transmit sensitive data; the instructions do not limit scope, do not require explicit justification, and could be used to collect or exfiltrate data.
Install Mechanism
No install specification or code files are present (instruction-only), which reduces the risk of arbitrary code being written to disk. This is lower-risk than arbitrary downloads, but the runtime instructions still assume access to local tooling and network.
Credentials
The document references storing secrets via environment variables and interacting with cloud platforms (AWS/GCP/Alibaba), yet the skill declares no required env vars or primary credential. That omission is a red flag: either required credentials are not declared (incoherent) or the skill expects the agent to look up credentials at runtime (dangerous).
Persistence & Privilege
The skill is not always-enabled and does not request elevated platform privileges, but the instructions include creating scheduled tasks and writing files (reminders, logs). Those behaviors can create persistence on the host if executed — consider this when allowing autonomous invocation.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install super-agent-skills
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /super-agent-skills 触发
  4. 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
v1.0.0
- Initial public release of super-agent-skills. - Provides a comprehensive AI Agent capability library with 20+ essential skills. - Covers areas including file operations, HTTP requests, scheduling, code execution, image/document generation, API/database integration, cloud services, message queues, containerization, CI/CD, authentication, encryption, security scanning, parallel processing, caching, logging, monitoring, and backup. - Includes best practices and environment checks for building robust, autonomous agents.
元数据
Slug super-agent-skills
版本 1.0.0
许可证 MIT-0
累计安装 1
当前安装数 1
历史版本数 1
常见问题

Super Agent Skills 是什么?

Comprehensive AI Agent capability library covering 20+ essential skills from file ops to cloud services, security, monitoring, and CI/CD. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 316 次。

如何安装 Super Agent Skills?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install super-agent-skills」即可一键安装,无需额外配置。

Super Agent Skills 是免费的吗?

是的,Super Agent Skills 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Super Agent Skills 支持哪些平台?

Super Agent Skills 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 Super Agent Skills?

由 Saqierma.a(@saqierma-cyber)开发并维护,当前版本 v1.0.0。

💬 留言讨论