The Agent Skills Directory

[SAFE]: The skill is composed exclusively of Markdown instructions, templates, and examples. It does not include any scripts, executables, or configuration files that could interact with the host system or network.
[EXTERNAL_DOWNLOADS]: A reference to the author's GitHub repository is provided in the provenance section. This is a static documentation link and does not trigger any automated downloads or remote code execution.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-provided descriptions of AI product ideas. Although no specific boundary markers are defined for this input, the risk is mitigated as the skill possesses no executable capabilities, file-writing tools, or network access that could be abused via injected instructions.

recommendation-canvas