The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill takes user inputs such as character_description and story_premise and directly interpolates them into instructions for image and video generation models.
Ingestion points: The inputs character_description and story_premise are defined in the frontmatter and used throughout the steps in SKILL.md.
Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the prompt templates.
Capability inventory: The skill utilizes the muapi CLI tool and curl to interact with external AI services for image and video generation.
Sanitization: There is no evidence of input validation, escaping, or filtering for the user-provided strings before they are sent to the AI models.
[COMMAND_EXECUTION]: The skill involves the execution of shell commands (muapi, curl, and potentially ffmpeg) to perform its tasks. Specifically, it suggests using curl with the $MUAPI_API_KEY environment variable to interact with the vendor's API. While this is functional for the skill's purpose, executing commands that include secrets can lead to credential exposure in process logs if the environment is not properly secured.

muapi-character-story-video