The Agent Skills Directory

[SAFE]: The skill consists entirely of instructional markdown and evaluation data for a generative video workflow. It contains no executable code, scripts, or external binary dependencies.\n- [SAFE]: No hardcoded credentials or sensitive data access patterns were found. API authentication details, such as Bearer token headers, are discussed conceptually for documentation purposes without providing actual secrets or keys.\n- [SAFE]: The skill includes explicit security and ethics instructions, such as requiring consent for performance capture (Act-Two) and mandating AI disclosure labels for generated content.\n- [SAFE]: The skill provides instructions to distinguish between content and commands when processing external data (e.g., comments or web results), helping to ensure the agent does not erroneously execute instructions embedded in data.

runway