The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the installation of the belt-sh/cli package via npx and references installation instructions hosted on GitHub (inference-sh/skills). These resources are necessary for the skill's operation and are directly related to the service provider.
[COMMAND_EXECUTION]: The skill utilizes the belt command-line tool to execute remote AI models for generating marketing assets. The allowed-tools configuration correctly limits the scope to the belt command.
[INDIRECT_PROMPT_INJECTION]: The skill defines an attack surface for indirect prompt injection as it processes natural language prompts to drive image and video generation tools.
Ingestion points: The prompt fields within the JSON --input blocks in SKILL.md used for AI model generation.
Boundary markers: Absent; the prompts are provided as direct string values within JSON objects without explicit delimiters.
Capability inventory: Invokes the belt CLI tool to perform network-based AI inference for asset creation.
Sanitization: Absent; the skill instructions do not provide methods for sanitizing or escaping user-provided prompt content.

app-store-screenshots