openai-whisper-api

Pass

Audited by Gen Agent Trust Hub on Jun 26, 2026

Risk Level: SAFEDATA_EXFILTRATIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: The skill sends audio data and the user's OpenAI API key to api.openai.com. This is the primary function of the skill and uses the official service endpoint.
  • [EXTERNAL_DOWNLOADS]: The skill uses curl to communicate with the OpenAI API for audio processing.
  • [COMMAND_EXECUTION]: The skill executes a shell script (scripts/transcribe.sh) that automates the transcription process using curl and handles directory creation for output files.
  • [PROMPT_INJECTION]: The skill processes untrusted audio data and converts it into text, creating a surface for indirect prompt injection.
  • Ingestion points: Transcription results are written to a file in scripts/transcribe.sh for the agent to process.
  • Boundary markers: None. The output does not include markers to separate transcribed text from instructions.
  • Capability inventory: Network access via curl and filesystem access for reading audio and writing transcripts.
  • Sanitization: None. Transcribed text is processed without filtering.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 26, 2026, 05:36 PM
Security Audit — agent-trust-hub — openai-whisper-api