The Agent Skills Directory

[SAFE]: The skill uses the infsh CLI and its associated applications (Tavily, Exa, Fal.ai) according to their intended professional use cases. All tool usage is properly scoped.
[EXTERNAL_DOWNLOADS]: The skill references installation instructions and additional components from the inference-sh GitHub repository, which is the official source for the tools described.
[PROMPT_INJECTION]: The skill processes external search results to generate persona data, which is an indirect prompt injection surface. This is a low-risk ingestion point as the skill does not possess high-privilege capabilities that could be abused by malicious content in search results. Ingestion points: search output from tavily/search-assistant and exa/search. Boundary markers: none. Capability inventory: Bash(infsh *) for research and image generation. Sanitization: none.

customer-persona