The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill incorporates user-provided text from the scene_description field directly into the generation prompt for the image editing phase. This represents a potential surface for indirect prompt injection where a user might attempt to override instructions through the input data.
Ingestion points: The scene_description input defined in SKILL.md is used to build prompts for the muapi image edit tool.
Boundary markers: The skill does not use delimiters or explicit 'ignore embedded instructions' warnings when interpolating user data into the prompt.
Capability inventory: The skill has the ability to execute CLI commands (muapi) and network operations (curl) which process the resulting data.
Sanitization: There is no evidence of input validation, filtering, or escaping for the user-supplied text before it is used in the prompt.
[COMMAND_EXECUTION]: The skill requires the agent to execute shell commands via the muapi CLI and curl to perform its core functions.
Instructions include calling muapi image edit, muapi video from-image, and muapi predict wait.
The skill provides a fallback mechanism using curl to interact with api.muapi.ai if specific models are not supported by the CLI.

muapi-product-video-ad-maker