Agent skill · Audited from source

subtitles

skill · zeropointrepo/youtube-skillsMIT licenceAudited 22 Oct 2026 · source 4c50c37e7438

★ 1,102pushed 1 day agoversion 1.5.1
!CAUTIONGrade B · 89/100 · 2 findings · 4c50c37
1,102repo stars · whole zeropointrepo/youtube-skills

Is it safe? With care — CAUTION, grade B (89/100). We read this skill's source at commit 4c50c37e7438 and found no filesystem, network or shell access and no hard-coded secrets. The audit raised 2 findings, 0 critical or high. What it does: Use when subtitles or the spoken text of a YouTube video is needed: pasted video links or IDs, requests to translate a video, read along, follow foreign-language content, or extract what was said. Also use for language…

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “subtitles (zeropointrepo/youtube-skills)”. Retrieved 22 Oct 2026. https://modelsatlas.com/skills/zeropointrepo/subtitles

Trust audit

Audit 0.4.1 · source read 22 Oct 2026

Trust score89/100!CAUTION B
0 critical0 high1 medium1 low0 info

CAUTION means the audit found things worth knowing before you trust this skill. Grade B is shared by 13,985 of 14,816 audited skills.

What the source does

  • FilesystemNone observedNo reads or writes in the source
  • NetworkNone observedNo outbound calls in the source
  • ShellNone observedNo commands run in the source
  • DependenciesPinnedNothing floats
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityPASS0
L1 Static sourceSecrets, path traversal, supply chain, hidden codeNA0
L2 InstructionsPrompt injection, authority framing, hidden directivesWARN2
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (2)

MEDIUMPrivilege escalation / persistencereview.unsafe_action · SKILL.md
F-06 Privilege escalation / persistenceCWE-269 · CWE-250Layer L2
Or let the agent create one for you.
Why
The package prompts the user to allow the agent to create a third-party account without any stated user consent gate.
Fix
rewrite it so the instruction says plainly what it does, and asks the user before it acts
LOWPrivilege escalation / persistencereview.unsafe_action · references/auth-setup.md
F-06 Privilege escalation / persistenceCWE-269 · CWE-250Layer L2
Store it persistently using whatever method is correct for this environment (which you determined in Step 0).
Why
The agent is directed to write a credential into persistent system configuration without requiring an explicit user confirmation step.
Fix
rewrite it so the instruction says plainly what it does, and asks the user before it acts

Audit 0.4.1 · source sha 4c50c37e7438 · 22 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publisherzeropointrepo GitHub organizationOwner of the repository this skill is read from
  • Source folderzeropointrepo/youtube-skills/clawhub/subtitlesThe exact folder we audited
  • LicenceMITAs the repository states it
  • Commit pinned for this verdict4c50c37e7438A new audit runs when the source changes
  • Repository statusNot archivedLast push 1 day ago
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Use when subtitles or the spoken text of a YouTube video is needed: pasted video links or IDs, requests to translate a video, read along, follow foreign-language content, or extract what was said. Also use for language…

---
name: subtitles
description: "Use when subtitles or the spoken text of a YouTube video is needed: pasted video links or IDs, requests to translate a video, read along, follow foreign-language content, or extract what was said. Also use for language learning or accessibility. Fetches timestamped subtitles from any YouTube video. Not for uploading subtitles or account management."
version: "1.5.1"
user-invocable: true
compatibility: Requires internet access to reach transcriptapi.com. No additional runtimes or dependencies needed.
required_environment_variables:
  - name: TRANSCRIPT_API_KEY
    prompt: Your TranscriptAPI key (starts with sk_)
    help: Free account at https://transcriptapi.com — 100 credits, no card required. Or let the agent create one for you.
    required_for: all API requests
metadata: {"openclaw":{"emoji":"🗨️","requires":{"env":["TRANSCRIPT_API_KEY"]},"primaryEnv":"TRANSCRIPT_API_KEY","homepage":"https://transcriptapi.com"},"hermes":{"tags":["youtube","subtitles","captions","transcripts","video","translation","language-learning"],"category":"media"}}
---

# Subtitles

Fetch YouTube video subtitles via [TranscriptAPI.com](https://transcriptapi.com).

## Setup

If `$TRANSCRIPT_API_KEY` is not set, read [references/auth-setup.md](references/auth-setup.md) and follow the instructions there to get and store the key.

## Required Headers

Every request needs two headers:

- **Authorization:** `Bearer $TRANSCRIPT_API_KEY`
- **User-Agent:** your agent's name and version if known (e.g. `HermesAgent/0.11.0`, `ClaudeCode/1.0`). Version is optional — agent name alone is fine. Do not omit this header or send a bare default — Cloudflare will return a 403 (error code 1010) and block the request.

## GET /api/v2/youtube/transcript

```bash
curl -s "https://transcriptapi.com/api/v2/youtube/transcript\
?video_url=VIDEO_URL&format=text&include_timestamp=false&send_metadata=true" \
  -H "Authorization: Bearer $TRANSCRIPT_API_KEY" \
  -H "User-Agent: YourAgent/1.0"
```

| Param               | Values                  | Use case                                       |
| ------------------- | ----------------------- | ---------------------------------------------- |
| `video_url`         | YouTube URL or video ID | Required                                       |
| `format`            | `json`, `text`          | `json` for sync'd subs with timing             |
| `include_timestamp` | `true`, `false`         | `false` for clean text for reading/translation |
| `send_metadata`     | `true`, `false`         | Include title, channel, description            |

**For language learning** — clean text without timestamps:

```bash
curl -s "https://transcriptapi.com/api/v2/youtube/transcript\
?video_url=VIDEO_ID&format=text&include_timestamp=false" \
  -H "Authorization: Bearer $TRANSCRIPT_API_KEY" \
  -H "User-Agent: YourAgent/1.0"
```

**For translation** — structured segments:

```bash
curl -s "https://transcriptapi.com/api/v2/youtube/transcript\
?video_url=VIDEO_ID&format=json&include_timestamp=true" \
  -H "Authorization: Bearer $TRANSCRIPT_API_KEY" \
  -H "User-Agent: YourAgent/1.0"
```

**Response** (`format=json`):

```json
{
  "video_id": "dQw4w9WgXcQ",
  "language": "en",
  "transcript": [
    { "text": "We're no strangers to love", "start": 18.0, "duration": 3.5 }
  ]
}
```

**Response** (`format=text`, `include_timestamp=false`):

```json
{
  "video_id": "dQw4w9WgXcQ",
  "language": "en",
  "transcript": "We're no strangers to love\nYou know the rules and so do I..."
}
```

## Tips

- Many videos have auto-generated subtitles in multiple languages.
- Use `format=json` to get timing for each line (great for sync'd reading).
- Use `include_timestamp=false` for clean text suitable for translation apps.

## Errors

| Code     | Meaning          | Action                                         |
| -------- | ---------------- | ---------------------------------------------- |
| 401      | Bad API key      | Check key                                      |
| 402      | No credits       | transcriptapi.com/billing                      |
| 403/1010 | Cloudflare block | Add or fix User-Agent header                   |
| 404      | No subtitles     | No subtitles available                         |
| 408      | Timeout          | Retry once after 2s                            |

1 credit per request. Free tier: 100 credits, 300 req/min.

Excerpt, first 4,411 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit 4c50c37

Download folder ↗
git clone https://github.com/zeropointrepo/youtube-skills
git -C youtube-skills checkout 4c50c37e7438

The author documents no install command, so this uses the repository directly. Our verdict covers commit 4c50c37e7438 only.

Works in which agents?

What its own text says, not a test

AgentStatusMore
Claude CodeMentioned in its text, not testedSkills for Claude Code · About Claude Code
OpenClawMentioned in its text, not testedSkills for OpenClaw · About OpenClaw
“Mentioned” means the skill’s text names the agent. We have not run it there.

Audit history

Every audit, every source change

  1. !CAUTION B 89 / 100

    first audit · source 4c50c37e7438

README badge

For maintainers · shows the latest audit

ModelsAtlas: CAUTION BMODELSATLASCAUTION · B
[![ModelsAtlas: CAUTION B](https://modelsatlas.com/skills/zeropointrepo/subtitles/badge.svg)](https://modelsatlas.com/skills/zeropointrepo/subtitles/)

The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.

Similar skills

yt✓SAFE

zeropointrepo/youtube-skills

Use when YouTube is relevant: pasted video links or IDs, @handles, quick video lookups, summaries, channel latest uploads, topic search, or any request involving YouTube content — even if YouTube is not mentioned…

★ 1.1kGrade B
youtube-channels✓SAFE

zeropointrepo/youtube-skills

Use when a YouTube channel is the focus: pasted @handles or channel URLs, requests to browse a creator's uploads, see what a channel has posted recently, search within a channel, or resolve a handle to a channel ID.…

★ 1.1kGrade B
youtube-data✓SAFE

zeropointrepo/youtube-skills

Use when structured YouTube data is needed: pasted video/channel/playlist links, transcripts for analysis, video metadata, channel upload history, search results, or playlist contents — without Google API quotas or…

★ 1.1kGrade B
youtube-playlist✓SAFE

zeropointrepo/youtube-skills

Use when a YouTube playlist is involved: pasted playlist links or IDs, requests to list playlist videos, browse playlist contents, or work through a playlist for transcripts or research. Also use when the user wants all…

★ 1.1kGrade B
youtube-search✓SAFE

zeropointrepo/youtube-skills

Use when the user wants to find YouTube content on any topic: searching for videos or channels, finding creators who cover a subject, discovering tutorials, talks, or expert discussions, or looking up a channel by name…

★ 1.1kGrade B
youtube-api✓SAFE

zeropointrepo/youtube-skills

Use when YouTube data is needed without Google API quotas or OAuth setup: transcripts, video metadata, channel info, search results, playlists. Triggers on pasted YouTube links, creator names, @handles, topic research,…

★ 1.1kGrade B

Add this badge to your README

[![ModelsAtlas: CAUTION B](https://modelsatlas.com/skills/zeropointrepo/subtitles/badge.svg)](https://modelsatlas.com/skills/zeropointrepo/subtitles/)

Questions about subtitles

What does the subtitles skill do?
YouTube Transcript API skills for AI agents. Get transcripts, search videos, browse channels. Works with OpenClaw, Hermes Agent, and other agent runtimes.
Is subtitles safe to install?
With care. The audit graded it B (89/100) and found 2 things worth knowing before you trust this skill, listed below with the exact line each was found on.
What can subtitles access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
Which assistants does subtitles work with?
Its documentation mentions claude-code and openclaw. That is what the text claims, not a compatibility test we ran.
How current is this page?
The grade is for one exact copy of the source (4c50c37e7438), read on 2026-10-22. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.