ZappushZappush
SkillsUse CasesBenchmarkCommunitySign In
      Back to Skills
      steipete

      Safety Report

      Openai Whisper Api

      @steipete

      Transcribe audio via OpenAI Audio Transcriptions API (Whisper).

      12,868Downloads
      640Installs
      25Stars
      1Versions
      API Integration4,971CLI & Shell Tools1,805Video & Audio1,618Networking & DNS1,102

      Security Analysis

      high confidence
      Clean0.08 risk

      The skill's code and runtime instructions match its stated purpose (calling OpenAI's /v1/audio/transcriptions with curl using an OPENAI_API_KEY); nothing in the files indicates unexpected data exfiltration or unrelated privileges.

      Feb 11, 20262 files2 concerns
      Purpose & Capabilitynote

      The skill's name/description (Whisper transcriptions) align with the included script which uses curl to call api.openai.com and uploads an audio file. Minor documentation inconsistency: top-level registry metadata lists no required env/bins, but SKILL.md metadata and the script require curl and OPENAI_API_KEY.

      Instruction Scopeok

      SKILL.md and scripts/transcribe.sh limit activity to reading the provided audio file, calling OpenAI's transcription endpoint, and writing the transcript to a local path. The script does not read unrelated files or send data to any third-party endpoints other than api.openai.com.

      Install Mechanismok

      No install spec; the skill is instruction-only with a small included shell script. Nothing is downloaded or written to system locations during install.

      Credentialsnote

      The only required credential is OPENAI_API_KEY, which is appropriate for this API. Note the SKILL.md suggests storing a key in ~/.clawdbot/clawdbot.json — storing API keys in plaintext files has risk if file permissions are lax. Also callout the mismatch between registry-level 'no required env' and the SKILL.md's declared requirements.

      Persistence & Privilegeok

      Skill does not request persistent/system-wide privileges, does not set always:true, and does not modify other skills or global agent settings.

      Guidance

      This skill is coherent for transcribing audio with OpenAI's Speech-to-Text API: it invokes curl to upload a local audio file to https://api.openai.com/v1/audio/transcriptions and requires an OPENAI_API_KEY. Before installing, ensure you (1) are comfortable providing an OpenAI API key (the script will send the audio to OpenAI), (2) have curl available on the host, and (3) if you choose to store the key in ~/.clawdbot/clawdbot.json, protect that file with strict permissions (chmod 600) or prefer environment variables to avoid plaintext storage. Also be aware of a small metadata mismatch in the registry (the top-level metadata omitted the declared requirement for curl and OPENAI_API_KEY in SKILL.md) — make sure the agent runtime will expose OPENAI_API_KEY when you run this skill.

      Latest Release

      v1.0.0

      More by @steipete

      Gog

      672 stars

      Github

      267 stars

      Weather

      229 stars

      Frontend Design

      186 stars

      Openai Whisper

      173 stars

      Nano Banana Pro

      164 stars

      Published by @steipete on ClawHub

      Zappush© 2026 Zappush
      HomeGuaranteeSupport

      Something feels unusual? We want to help: [email protected]