The Agent Skills Directory

[SAFE]: The skill instructions define standard assistant behavior for document generation. It uses interactive questioning and structured templates to help users build PRDs.
[COMMAND_EXECUTION]: The documentation provides examples for users to manually initialize their workspace using shell commands (mkdir, touch), but the skill logic itself does not automate dangerous system operations.
[EXTERNAL_DOWNLOADS]: While the skill involves searching for competitor information as part of its primary PRD research function, it does not download or execute remote scripts from untrusted sources.
[PROMPT_INJECTION]: No evidence of instructions designed to bypass agent safety filters or override system constraints was found.
[DATA_EXFILTRATION]: The skill operates on user-provided product ideas and public research data. There are no attempts to access sensitive system files or exfiltrate private credentials.

prd-generator