The Agent Skills Directory

[SAFE]: The skill consists entirely of instructional markdown files and YAML metadata. It does not include any executable code or scripts.
[EXTERNAL_DOWNLOADS]: The skill references several external resources in references/sources.md, including UNESCO, the EU AI Act, and C2PA technical specifications. These are established international organizations and industry standards. It also links to the author's own blog and repository on dev.to and github.com, which are identified as legitimate vendor resources.
[INDIRECT_PROMPT_INJECTION]: The skill defines a framework for handling external narratives. While it provides a surface for processing untrusted text, the instructions focus on manual curation and disclosure (role ledgers) rather than automated processing, and no exploitable capabilities or tools are invoked.

storytelling-ethics-lifecycle