skills/lalalic/bullx/tts-stt-sts/Gen Agent Trust Hub

tts-stt-sts

Pass

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads a sample audio file from https://cdn.qili2.com/pub/voice/ray/sichuan.mp3 using curl for use in a voice cloning example.
  • [COMMAND_EXECUTION]: The skill executes shell commands using uvx to run mlx-audio and whisper CLI tools and uses ffmpeg for audio format conversion.
  • [PROMPT_INJECTION]: The skill ingests external data which represents a surface for indirect prompt injection. 1. Ingestion points: Reads text from local files like script.txt and ref_normal.txt (SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: Uses uvx to call Python-based CLI tools, curl for downloads, and ffmpeg for audio conversion (SKILL.md). 4. Sanitization: No explicit sanitization or validation of the input text files is performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 24, 2026, 12:12 AM