The Agent Skills Directory

[NO_CODE]: The skill is composed entirely of instructional Markdown files and configuration YAML. It does not include any Python scripts, Node.js code, shell commands, or binary executables.
[SAFE]: The instructions focus on manual verification of content assets, captions, and disclosure requirements. No automated actions or dangerous operations were detected.
[INDIRECT_PROMPT_INJECTION]: While the skill instructions involve reviewing external content (such as social media captions), the skill lacks any execution capabilities or tool access (subprocess, network, file writing) that could be exploited via injection. The ingestion points include content provided by the user for review in SKILL.md, but there are no capabilities to inventory and no automated sanitization is required for this purely instructional use case.

publishing-checklist