The Agent Skills Directory

[SAFE]: The skill consists entirely of text-based guidelines for writing spoken voiceovers. It does not include any executable code, shell commands, or network operations.- [NO_CODE]: There are no scripts, binaries, or external dependencies associated with this skill. It functions purely as a set of prompt instructions.- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied information to create scripts. This represents a potential attack surface for indirect prompt injection. However, the risk is negligible because the skill does not have access to any dangerous tools or sensitive data. Findings for this category: (1) Ingestion points: User-provided storyboard or tutorial descriptions; (2) Boundary markers: Absent; (3) Capability inventory: None (no shell, file, or network access); (4) Sanitization: Absent.

Narration Script