The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: References external documentation and installation instructions hosted on the inference-sh GitHub repository.
[COMMAND_EXECUTION]: Utilizes the belt CLI tool to execute remote AI applications and perform web-based research tasks.
[PROMPT_INJECTION]: The skill identifies an indirect prompt injection surface due to the ingestion of untrusted external data.
Ingestion points: External content is retrieved via belt app run tavily/search-assistant and belt app run exa/search as shown in SKILL.md.
Boundary markers: The skill does not implement specific boundary markers or instructions to disregard potential commands embedded within the retrieved search results.
Capability inventory: The skill leverages the belt command-line tool for remote application execution and has access to the shell as restricted by the allowed-tools configuration.
Sanitization: No explicit sanitization or validation of external search data is performed before it is incorporated into the agent's context.

product-hunt-launch