The Agent Skills Directory

[SAFE]: The skill is entirely composed of markdown instructions and templates designed to guide the AI's generation of thumbnail concepts. It does not include any scripts, command-line executions, or system-level operations.
[INDIRECT_PROMPT_INJECTION]: The skill processes external data via the $ARGUMENTS placeholder (typically video titles). While it lacks explicit sanitization or boundary instructions, it possesses no exploitable capabilities such as file writing, network requests, or shell command execution, eliminating the risk associated with this attack vector.
Ingestion points: The $ARGUMENTS variable in SKILL.md used for video titles.
Boundary markers: Uses bold markdown syntax **$ARGUMENTS** but lacks explicit instructions to disregard embedded commands.
Capability inventory: No file system access, network operations, or code execution capabilities detected.
Sanitization: No specific input sanitization or filtering is implemented.

thumbnail-psychology