The Agent Skills Directory

[SAFE]: The skill operates as intended, providing users with a framework for video creation using the inference.sh service. No malicious instructions, hidden code, or unauthorized behaviors were detected.
[COMMAND_EXECUTION]: The skill makes use of the infsh CLI via Bash to perform video and audio generation tasks. This usage is authorized and follows the core purpose of the skill.
[EXTERNAL_DOWNLOADS]: The skill refers to external resources such as the infsh CLI and related skills from the inference-sh ecosystem. These are provided by the vendor and are treated as safe, legitimate dependencies.
[PROMPT_INJECTION]: The skill constructs prompts for AI models using user-supplied inputs. While this identifies an attack surface for indirect prompt injection, the skill itself does not contain malicious override attempts, and the risk is considered low in the context of media generation.

ai-marketing-videos