The Agent Skills Directory

[SAFE]: The skill consists entirely of instructional markdown content designed to guide the agent through a logical categorization process. It does not include any scripts, executable code, or system-level commands.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process external data such as Project Requirements Documents (PRDs) or feature sets provided by the user. While this constitutes an ingestion surface for untrusted data, the skill has no dangerous capabilities (no network access, no file system write permissions, and no command execution), making the risk of exploitation negligible.

scope