← 返回 Skills 市场
snazar-faberlens

Sag Hardened

作者 Faberlens · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ 安全检测通过
35
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install sag-hardened
功能描述
ElevenLabs text-to-speech with mac-style say UX.
安全使用建议
This skill appears coherent for local ElevenLabs TTS use. Before installing: (1) Inspect the Homebrew formula (steipete/tap/sag) or the tap's repository to confirm it's legitimate and see what it installs or runs; (2) keep your ELEVENLABS_API_KEY in a secure place (environment variable or secrets manager) and never paste it into commands or files; (3) the SKILL.md already warns against exfiltration—don’t pipe audio or keys to network commands; (4) consider running the sag CLI manually first to verify expected behavior and any network endpoints it contacts. If you need lower supply-chain risk, prefer installing sag from a well-known or audited source or review the formula source before brew install.
功能分析
Type: OpenClaw Skill Name: sag-hardened Version: 1.0.0 The 'sag-hardened' skill provides a wrapper for the ElevenLabs TTS CLI (sag). It is notable for including explicit defensive instructions in SKILL.md and SAFETY.md designed to prevent the AI agent from leaking API keys, performing unauthorized network exfiltration, or incurring excessive costs through bulk generation. The installation process uses a reputable Homebrew tap (steipete/tap/sag), and the overall intent of the bundle is clearly focused on security hardening and safe agent behavior.
能力标签
requires-sensitive-credentials
能力评估
Purpose & Capability
Name/description (ElevenLabs TTS with mac-style UX) match the declared requirements: a 'sag' CLI binary and ELEVENLABS_API_KEY. No unrelated env vars, binaries, or config paths are requested.
Instruction Scope
SKILL.md instructs the agent to call the local 'sag' CLI, generate audio to local paths (e.g., /tmp/voice-reply.mp3), and include the file in replies. It explicitly warns against exposing or transmitting API keys and against piping outputs to network commands. The instructions do not ask for unrelated files, credentials, or system state.
Install Mechanism
Install uses a Homebrew formula from a third-party tap (steipete/tap/sag). Brew formulas are common and reasonable, but third-party taps carry more provenance risk than an official tap — review the formula/source (GitHub) before installing to confirm no unexpected network behavior or post-install hooks.
Credentials
Only ELEVENLABS_API_KEY is required (declared as primary). The SKILL.md also references optional voice-related env vars by name, but no extraneous credentials are requested.
Persistence & Privilege
always is false, no config paths requested, and the skill is instruction-only (no code written to disk by the skill itself). Agent autonomous invocation is allowed but is the platform default and not a special privilege here.
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 sag-hardened
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /sag-hardened 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 release of sag-hardened 1.0.0 - Adds ElevenLabs text-to-speech with a mac-style say command-line experience. - Supports various ElevenLabs models (expressive, stable, fast), with quick-start commands and voice selection. - Provides robust pronunciation, delivery rules, and audio tag support for nuanced voice outputs. - Includes detailed security guardrails to protect API keys and avoid accidental overuse or exposure. - Features installer via Homebrew and environment variable setup instructions.
元数据
Slug sag-hardened
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

Sag Hardened 是什么?

ElevenLabs text-to-speech with mac-style say UX. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 35 次。

如何安装 Sag Hardened?

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

Sag Hardened 是免费的吗?

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

Sag Hardened 支持哪些平台?

Sag Hardened 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 Sag Hardened?

由 Faberlens(@snazar-faberlens)开发并维护,当前版本 v1.0.0。

💬 留言讨论