The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill references the installation of the belt CLI tool via npx skills add belt-sh/cli and links to documentation hosted on GitHub. These dependencies are necessary for the skill's primary function of interfacing with the inference.sh platform.
[COMMAND_EXECUTION]: The skill utilizes the belt command-line utility for authentication, searching for AI models, and executing video generation tasks. The allowed-tools configuration in the YAML frontmatter limits the agent's capability to this specific tool within the Bash environment, adhering to the principle of least privilege.
[INDIRECT_PROMPT_INJECTION]: The skill provides a surface for indirect prompt injection as it interpolates user-supplied text into the --input field of the belt command.
Ingestion points: User-provided strings for the prompt field in the command examples found in SKILL.md.
Boundary markers: None present.
Capability inventory: Execution of the belt CLI tool via Bash.
Sanitization: None present; the skill relies on the inference platform's internal content filters to handle adversarial prompts.

google-veo