The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external search providers (Tavily and Exa) to gather industry context and benchmarks.
Ingestion points: Results from tavily/search-assistant, exa/search, and exa/answer are brought into the agent's context in SKILL.md.
Boundary markers: The skill does not define specific delimiters or instructions to ignore potential malicious content embedded in search results.
Capability inventory: The skill has access to file-writing tools (via Python execution) and further network operations via the belt CLI.
Sanitization: No explicit sanitization or filtering of the external search content is performed before processing.
[DYNAMIC_EXECUTION]: The skill uses the infsh/python-executor app to run Python code at runtime for the purpose of generating data visualization charts.
Evidence: A script using matplotlib is passed as input to belt app run infsh/python-executor to generate results-chart.png.
[EXTERNAL_DOWNLOADS]: The skill references installation instructions and tools hosted on external domains associated with the platform's infrastructure.
Evidence: References to npx skills add belt-sh/cli and configuration guidelines hosted at raw.githubusercontent.com/inference-sh/skills/.
[COMMAND_EXECUTION]: The skill facilitates the execution of shell commands through the belt CLI tool, which is scoped within the allowed-tools frontmatter to manage application runs and research queries.

case-study-writing