← 返回 Skills 市场
subtitle-refiner
作者
TrueTechLabs
· GitHub ↗
· v1.0.0
· MIT-0
336
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install subtitle-refiner
功能描述
智能优化 SRT 字幕，去除语气词并修正 ASR 错误，保持时间戳不变，输出优化文件并发送飞书通知及 token 报告。
安全使用建议
Before installing or enabling this skill: 1) Treat SILICONFLOW_API_KEY as required despite the top-level registry metadata omission; do not set a production key until you review/modify the code. 2) Inspect scripts/refine.py completely (the visible portion already prints the Bearer token and entire request/response JSON to stderr) — remove or silence any logging that prints the API key or full response bodies. 3) Verify how Feishu file sending is authenticated (the SKILL.md asks for chat_id but provides no Feishu token variable); confirm there is no hidden upload endpoint or unexpected external recipient. 4) Consider running the skill in an isolated environment with a throwaway API key and without sensitive subtitles to observe behavior. 5) Ask the author to fix the manifest inconsistency (declare required env vars) and to stop logging secrets and full user content. If you cannot confirm these fixes, do not provide real API keys or sensitive files to this skill.
功能分析
Type: OpenClaw Skill
Name: subtitle-refiner
Version: 1.0.0
The skill is functional and performs its stated task of subtitle refinement; however, it contains a significant security flaw in `scripts/refine.py`. The script explicitly prints the sensitive `SILICONFLOW_API_KEY` to `stderr` during the `call_siliconflow_api` function for debugging purposes. While this appears to be a verbose logging practice rather than intentional malice, it results in the leakage of API credentials into process logs, meeting the criteria for a 'suspicious' classification due to high-risk vulnerability.
能力评估
Purpose & Capability
The description, SKILL.md and code all describe using the SiliconFlow LLM to refine SRT files, so requiring SILICONFLOW_API_KEY is coherent with purpose. However the registry metadata at the top (Required env vars: none) contradicts SKILL.md and the code which expect SILICONFLOW_API_KEY — an inconsistency that should be resolved before trusting the skill.
Instruction Scope
SKILL.md instructs the agent to run scripts/refine.py and to obtain a Feishu chat_id from context and a workspace dir. The script (visible portions) logs full request payloads and the Authorization header (Bearer <API_KEY>) and full response JSON to stderr — this will expose the API key and user's subtitle content in logs. SKILL.md also promises sending files to Feishu but does not declare any Feishu credentials or explain how auth is performed, creating ambiguity about where data and files are sent and what credentials are used.
Install Mechanism
There is no external installer or remote download; the skill is instruction-only with packaged Python scripts. That reduces installer risk. The skill does rely on Python and the requests library (which may need to be present), but no high-risk install URL or archive extraction is present.
Credentials
Requiring SILICONFLOW_API_KEY is proportionate to using SiliconFlow. However: (1) the registry metadata omitted that requirement (incoherent declarations); (2) the script prints the API key to stderr (leaks a secret); and (3) the skill sends output to Feishu but does not declare Feishu credentials/environment variables, so it's unclear what credentials the script will use to post files — this ambiguity plus explicit key-leaking is a privacy/security concern.
Persistence & Privilege
The skill is not set to always:true and does not request system-wide configuration changes. It does include code that will be executed (Python), but it does not request permanent platform privileges in the manifest.
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 subtitle-refiner - 安装完成后，直接呼叫该 Skill 的名称或使用
/subtitle-refiner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
v1.0.0
Initial release of subtitle-refiner – a tool for optimizing SRT subtitle files.
- Removes filler words (e.g., 嗯, 啊) and corrects ASR recognition errors (e.g., XGBT→ChatGPT) while preserving timestamps.
- Sends optimized files and token usage reports via Feishu.
- Requires Python 3 and a SILICONFLOW_API_KEY environment variable.
- Provides clear error handling and token consumption tracking.
- User-invocable by sending SRT files or trigger keywords (e.g., "优化字幕", "fix subtitle").
元数据
常见问题
subtitle-refiner 是什么？
智能优化 SRT 字幕，去除语气词并修正 ASR 错误，保持时间戳不变，输出优化文件并发送飞书通知及 token 报告。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 336 次。
如何安装 subtitle-refiner？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install subtitle-refiner」即可一键安装，无需额外配置。
subtitle-refiner 是免费的吗？
是的，subtitle-refiner 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
subtitle-refiner 支持哪些平台？
subtitle-refiner 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 subtitle-refiner？
由 TrueTechLabs（@truetechlabs）开发并维护，当前版本 v1.0.0。
推荐 Skills