07 Subtitle Gen

Generate synced SRT subtitles locally from dialogue text and durations without API, ensuring platform-compatible timed captions for videos.

Security Scan

The skill claims to generate synced SRT subtitles from audio locally, but the implementation is a stub that ignores the audio_url and returns a fixed 3-second SRT containing the provided dialogue — coherent purpose but inconsistent implementation.

Purpose & Capability

The manifest and SKILL.md claim to generate synced subtitles from an audio input. The included code never fetches or analyzes audio_url, does not compute timings from audio, and simply returns a single static 00:00:00 --> 00:00:03 caption with the dialogue appended. The required input (audio_url) is declared but unused, and no actual subtitle file is created or hosted despite returning a subtitle_url string. This is an implementation mismatch with the stated purpose.

Instruction Scope

SKILL.md stays within the narrow scope of local subtitle generation and does not instruct reading unrelated files or contacting external endpoints. However, the runtime instructions and the code disagree: the docs imply real audio processing, but runtime code is a trivial stub. That mismatch is concerning because users (or agents) will expect behavior the skill does not provide.

Install Mechanism

No install spec and no external downloads. The skill is instruction-only with a tiny included Node.js entrypoint; nothing is written to disk or fetched during install. Low install risk.

Credentials

No environment variables, credentials, or config paths are requested. The declared surface is minimal and proportionate to the claimed local operation.

Persistence & Privilege

always is false and the skill does not request persistent system-level privileges or attempt to modify other skills or agent-wide settings. Normal user-invocable behavior.

What to consider before installing

This skill is low-risk from a security perspective (no network calls, no credentials, no install), but it's misleading: it advertises synced subtitle generation from audio yet the code ignores the audio_url and returns a static 3-second SRT fragment. Before installing or using it, consider: 1) Do not rely on this for production — test it with non-sensitive audio to confirm behavior. 2) Ask the author for a correct implementation that actually processes audio and writes/hosts the SRT, or modify the code yourself. 3) Be aware that subtitle_url is just a filename string; the skill does not create or expose a real file or URL. If you need real audio-to-timestamped subtitles, choose a different, well-implemented skill or request additional code that genuinely analyzes audio.

自动字幕生成技能

功能介绍

根据音频自动生成带时间轴的标准SRT字幕。

输入参数

• audio_url：音频地址（必填）
• dialogue：台词文本（可选）

输出结果

• subtitle_url：SRT字幕文件地址

使用场景

• 短剧自动加字幕
• 短视频快速字幕制作
• 批量音视频字幕生成

技术说明

纯本地运行，无需API、无需模型配置。