The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the installation of the belt-sh/cli package and references a remote installation guide located at https://raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.md.
[COMMAND_EXECUTION]: The skill utilizes the belt CLI tool to run remote applications for image generation (falai/flux-dev-lora, bytedance/seedream-4-5) and research (tavily/search-assistant, exa/answer).
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external search providers, which constitutes a potential attack surface for indirect prompt injection.
Ingestion points: External research data retrieved via the tavily/search-assistant and exa/answer applications in SKILL.md.
Boundary markers: No specific delimiters or safety instructions are provided to the agent to distinguish between its primary instructions and the untrusted data from tool outputs.
Capability inventory: The skill possesses the capability to execute shell commands using the belt tool, allowing it to act on information gathered from the search tools.
Sanitization: The skill does not specify any sanitization, filtering, or validation steps for the content returned by external research tools.

landing-page-design