groq-stt
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external audio files which may contain instructions that could influence the agent's behavior if the resulting transcription is subsequently processed. \n
- Ingestion points: The script
scripts/transcribe.mjsreads audio data usingfs.readFileSync. \n - Boundary markers: No delimiters or security warnings are used to isolate the transcribed output. \n
- Capability inventory: The skill has file-writing capabilities (
fs.writeFileSync). \n - Sanitization: The transcription result is processed without validation or filtering. \n- [DATA_EXFILTRATION]: The script reads local audio files provided as arguments and transmits their content to the Groq API (api.groq.com) for processing.
Audit Metadata