skills/yaoapp/yao/yao-audio/Gen Agent Trust Hub

yao-audio

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external audio files via the audio_path parameter. This creates a surface where instructions embedded in the audio content, once transcribed into text, could be interpreted by the agent. Ingestion points: audio_path parameter in audio_transcribe tool (SKILL.md). Boundary markers: Absent. Capability inventory: tai CLI tool execution (SKILL.md). Sanitization: Absent.
  • [COMMAND_EXECUTION]: The skill executes the tai CLI tool to perform its primary functions, including audio transcription and listing available providers. This is the intended behavior for the skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 11:21 AM