The Agent Skills Directory

[SAFE]: The skill is entirely composed of Markdown documentation, guidelines, and templates. It does not contain any executable scripts, binaries, or active code components.
[SAFE]: No sensitive information such as API keys or credentials is hardcoded. Data handling practices described in the instructions emphasize privacy, consent, and data minimization.
[SAFE]: No signs of obfuscation, remote code downloads, or unauthorized network communication were identified across any of the files.
[SAFE]: The skill processes untrusted user feedback, creating a surface for indirect prompt injection. However, it lacks dangerous capabilities (network access, file system writes, or command execution) that would make such an injection exploitable. It also provides defensive recommendations such as using structured output schemas and synthetic feedback detection.

voice