The Agent Skills Directory

[SAFE]: The skill consists of instructional markdown files and configuration data. A thorough review of all six files, including the primary SKILL.md and reference materials, found no evidence of malicious command execution, unauthorized data access, or persistence mechanisms.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze untrusted user input, such as script fragments and AI-video prompts. While this is a theoretical entry point for indirect prompt injection, the skill lacks any capabilities—such as file writing, shell access, or external network requests—that could be leveraged for an exploit. The risk is considered negligible as the agent's output is limited to text-based analysis within the user's session.

shot-information-progression