youtube-whisper@0.1.0
VERIFIED· not startedPublisher claims: "Enables AI agents to obtain verbatim timestamped YouTube audio transcriptions and extract native HD keyframes at exact moments, along with video metadata, channel listings, and Groq quota health checks." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Not started: dependency install failed; the server itself was not observed.- Tested
- the dependency install step · every file read, file written and host contacted by what ran
- Not tested
- server startup · the tool list · tool behavior
What this means for the label: Verified here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.
Before you give it your token
Code inventory arrives with this version's next honeypot run.- It will ask for
- unknown until the next run
- Where it talks to
- unknown until the next run
- What the honeypot saw
- no credential files read · no network
- What we could not test
- server startup · the tool list · tool behavior
Not enough was observed to say yet. Not started: dependency install failed; the server itself was not observed. This version's code has not been inventoried for credentials and hosts either; both arrive with its next honeypot run (popular servers first). `vet-skills try youtube-whisper` runs it now and prints the full answer.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-07 and scored it 87/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 2 scenarios · 0 deviationsStatic findings
return subprocess.run(cmd, capture_output=True, text=True, check=check)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.assert sanitize_filename("../../../etc/passwd") == "etcpasswd"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.description: "Pipeline transkripsi verbatim YouTube (Whisper Large V3) dan ekstraksi keyframe visual HD kilat untuk riset video agen AI."Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.| `transcribe_youtube` | Unduh audio, chunking cerdas (<25MB), dan transkripsi verbatim lengkap dengan timestamp rapi (`.md` dan `_raw.json`). | `url` (str), `output_path` (str, opsional), `language` Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.Server `youtube-whisper` otomatis mendeteksi file ini, memutar giliran key, dan menangani jeda cooldown secara transparan.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.2. **Kebutuhan Akurasi Verbatim (Ground Truth)**: Jangan pernah mengandalkan *auto-captions* bawaan YouTube yang sering memotong angka, menghilangkan tanda baca, atau salah mengeja ticker finansial daFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.Pipeline standar untuk riset mendalam video YouTube menggunakan transkripsi verbatim (kata per kata) lossless via Groq Whisper Large V3 dan ekstraksi frame visual HD (720p/1080p) otomatis via HLS rangFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.3. **Verifikasi Visual (Charts, Slides, Formula)**: Saat transkrip merujuk pada visual ("lihat di chart ini", "seperti pada slide"), panggil tool `extract_keyframe` untuk menarik gambar HD di timestamFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.| `check_groq_quota` | Periksa ketersediaan key pool dan sisa waktu cooldown | - |Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.- **Agent SOP Ready (`SKILL.md`):** Disertai panduan metodologi riset untuk agen AI agar tidak membuat ringkasan dangkal (*lazy summary*), wajib inline screenshot, dan aturan anti-LaTeX.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.- **Transkripsi Verbatim Murni (Bukan Auto-Caption):** Mengunduh trek audio original (menolak track auto-dubbing AI), decode satu kali ke FLAC 16 kHz mono (SoX resampler), dan mentranskripsi dengan prFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.- **Multi-Key Pool & 429 Failover:** Rotasi otomatis multi-key Groq API. Jika salah satu key menyentuh rate limit 429, sistem membaca header `retry-after`, menaruh key dalam status cooldown, dan langsFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.Cost to the agent
Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.
Known vulnerabilities
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.