The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill recommends installing the belt-sh/cli package and references installation documentation hosted on the official inference-sh GitHub repository.
[COMMAND_EXECUTION]: Uses the belt CLI for authenticated login and to run utility apps for industry research, such as tavily/search-assistant and exa/search.
[REMOTE_CODE_EXECUTION]: Provides a template for generating before/after comparison charts using the infsh/python-executor tool. The provided Python script uses matplotlib and is designed for static data visualization based on the case study metrics.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it ingests data from external search tools while possessing code execution capabilities.
Ingestion points: External data enters the context via tavily/search-assistant and exa/search tool outputs as instructed in SKILL.md.
Boundary markers: No specific delimiters or instructions to ignore embedded commands are included for the agent when processing search results.
Capability inventory: The skill has access to the Bash(belt *) toolset and the infsh/python-executor environment.
Sanitization: There is no evidence of sanitization or validation of the external content retrieved from the search tools before it is processed by the agent.

case-study-writing