The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text prompts to generate video content. This represents an ingestion point for untrusted data, though it is the primary intended function of the skill. The execution environment is restricted to the infsh CLI tool via allowed-tools constraints.
Ingestion points: User-provided prompts within the --input JSON field for infsh app run commands in SKILL.md.
Boundary markers: None explicitly defined in the provided command examples.
Capability inventory: Execution of infsh commands via the Bash tool, restricted by allowed-tools in SKILL.md.
Sanitization: The skill instructions do not specify explicit sanitization or escaping of the prompt input before command interpolation.
[EXTERNAL_DOWNLOADS]: The documentation references external installation instructions and configuration for the infsh CLI tool hosted on the official GitHub repository for the inference-sh platform and documentation site.

p-video