The Agent Skills Directory

[SAFE]: The skill is a purely instructional document (SKILL.md) that outlines a decision-making framework for selecting video topics. It does not contain any executable scripts, shell commands, or network requests.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided data such as personal experiences and trending topics. However, since the skill has no access to sensitive system resources, file writing capabilities, or external network APIs, the risk of a successful indirect prompt injection attack causing harm is negligible.
[DATA_EXPOSURE_AND_EXFILTRATION]: No patterns related to accessing sensitive files (like .env or .ssh) or exfiltrating data via network protocols (curl, wget, etc.) were found.

tslj-idea