The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the internet through search tools and browser agents, which could be manipulated by external parties to influence the agent's logic.
Ingestion points: Uses tavily/search-assistant, exa/search, and infsh/agent-browser in SKILL.md to fetch web content and search results.
Boundary markers: Absent. The skill does not implement delimiters or safety instructions to separate external data from system prompts.
Capability inventory: The skill has the ability to execute Python code via infsh/python-executor, write files (PNG maps), and perform browser operations.
Sanitization: No sanitization, escaping, or validation of the retrieved web content is performed.
[EXTERNAL_DOWNLOADS]: The skill references and downloads components from the developer's infrastructure and well-known services.
Fetches installation guidelines from the inference-sh GitHub repository.
References the official inference.sh CLI and vendor-specific NPM packages.
[DYNAMIC_EXECUTION]: The skill includes a static Python template that is executed at runtime to generate data visualizations.
Uses matplotlib to generate and save a positioning map as positioning-map.png.
[COMMAND_EXECUTION]: The skill uses the belt CLI tool to orchestrate research tasks, application runs, and image processing.

competitor-teardown