The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the infsh CLI tool to execute AI model workloads. This is limited to the specific command via the allowed-tools restriction in the frontmatter.
[EXTERNAL_DOWNLOADS]: The documentation suggests installing additional related skills from the inference-sh organization using npx skills add. These are vendor-owned resources and are part of the intended functionality.
[PROMPT_INJECTION]: The skill processes untrusted data which creates a surface for indirect prompt injection.
Ingestion points: The skill accepts user-provided strings for prompt and external URLs for image_url, video_url, and audio_url within the JSON input to the infsh command.
Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are present in the provided examples.
Capability inventory: The skill possesses the capability to execute shell commands via the infsh tool, which interacts with remote AI services.
Sanitization: There is no evidence of input sanitization or validation for the URLs or prompt content within the skill instructions.

ai-video-generation