The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill provides instructions to install the belt-sh/cli and additional modular skills from the inference-sh GitHub repository. These downloads are necessary for the skill's core functionality.
[COMMAND_EXECUTION]: Uses the belt CLI tool to run specific applications for searching, image generation, and social media posting. These commands are transparently documented as part of the intended workflow.
[REMOTE_CODE_EXECUTION]: Includes an example that executes a Python script within the infsh/python-executor environment. The script is used for data visualization (plotting a chart with matplotlib) and is explicitly visible in the skill instructions.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes external data from web searches and HTML templates.
Ingestion points: Search query inputs in exa/search and HTML content in infsh/html-to-image within SKILL.md.
Boundary markers: Data is passed through structured JSON fields.
Capability inventory: The agent can execute system commands, run Python scripts, and perform network requests via the belt CLI.
Sanitization: No explicit sanitization of external search results or HTML inputs is defined.

technical-blog-writing