The Agent Skills Directory

[SAFE]: The skill's primary function is content transformation using predefined templates and local reference files. No evidence of malicious command execution, unauthorized file system access, or network exfiltration was detected.
[PROMPT_INJECTION]: Although the skill processes external data (Source URLs and content atoms) which could serve as a surface for indirect prompt injection, it does not contain instructions that override safety filters or manipulate the agent's behavior. The output is confined to writing markdown files in a specific directory.

repurpose-youtube