The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The instructions guide the user to install external components and skills using commands like npx skills add belt-sh/cli and npx skills add inference-sh/skills@.... These external packages are sourced from repositories not identified as trusted vendors.
[EXTERNAL_DOWNLOADS]: The skill refers to an external installation guide and configuration file at https://raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.md.
[COMMAND_EXECUTION]: The skill uses the Bash tool to execute belt CLI commands for image generation and account management.
[INDIRECT_PROMPT_INJECTION]: The skill constructs commands that interpolate user-provided prompt strings into JSON inputs for AI models. This creates a potential vulnerability where untrusted data could influence the behavior of the generation tools.
Ingestion points: The prompt field within the JSON input of belt app run commands.
Boundary markers: Absent; the instructions provide direct interpolation examples without delimiters.
Capability inventory: The skill can execute shell commands via Bash(belt *) to perform image generation and app management.
Sanitization: No sanitization or validation of the input prompt strings is implemented within the skill instructions.

youtube-thumbnail-design