music-lyrics
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external audio data and converts it to text (transcription). This creates an attack surface where malicious instructions spoken in the audio could influence the agent's behavior.
- Ingestion points: The skill ingests audio files via the
<audio_file_path>argument for transcription as described inSKILL.md. - Boundary markers: The instructions do not define clear boundaries or delimiters to isolate the transcribed text from agent instructions.
- Capability inventory: The skill has the ability to execute shell commands using
python3 -m music_analyzer. - Sanitization: No sanitization, escaping, or filtering of the transcribed text is mentioned before it is presented to the agent's context.
Audit Metadata