The Agent Skills Directory

[SAFE]: The skill is composed entirely of informational content and instructions for an AI agent. No code, scripts, or executable commands are present within the skill files.
[SAFE]: There are no external downloads, network requests, or hardcoded credentials. All operations described are textual transformations performed by the AI model.
[SAFE]: Although the skill accepts external data for analysis (survey results), it lacks any capability (such as file writing or network access) that would allow for exploitation via indirect prompt injection.

pmf-survey