mc-ai-tell-audit
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a documentation-based resource providing guidelines for auditing generative music models. It consists of evaluation criteria, thresholds, and diagnostic paths without any executable scripts or functional code.
- [EXTERNAL_DOWNLOADS]: Mentions the tool 'demucs' for vocal track separation. This is a well-known open-source tool in the audio processing community. The skill does not provide any commands to download or execute it automatically.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a process for ingesting and analyzing untrusted generated audio output. While this represents a potential attack surface, the skill lacks the necessary tool-calling or shell-execution capabilities to allow embedded data to compromise the agent's security.
Audit Metadata