The Agent Skills Directory

[SAFE]: The skill consists entirely of instructional Markdown content and does not include any executable scripts, binaries, or package dependencies. This absence of code eliminates standard attack vectors such as remote code execution or privilege escalation.
[SAFE]: No evidence of data exfiltration, obfuscation, or malicious instructions was found. The skill operates exclusively on user-provided music metadata to generate text-based suggestions.
[SAFE]: The skill processes untrusted user data such as lyrics and video descriptions, which is a common surface for indirect prompt injection. However, no specific vulnerabilities were found. 1. Ingestion points: user-provided lyrics and video descriptions; 2. Boundary markers: absent; 3. Capability inventory: text generation of titles and hooks; 4. Sanitization: none specified.

bmz-publish