genmedia-audio-engineer
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references an external URL for a prompt guide (https://deepmind.google/models/lyria/prompt-guide/). This points to an official documentation site managed by Google DeepMind, which is a recognized and trusted source.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided natural language prompts to generate music and speech via tools like
lyria_generate_musicandgemini_audio_tts. While these inputs are interpolated into tool parameters, the instructions focus on creative audio generation and professional mixing workflows. Standard safeguards for LLM-driven tool invocation apply.
Audit Metadata