The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill provides a link to installation instructions for the vendor's CLI tool (infsh) hosted on their official GitHub repository.
[DYNAMIC_EXECUTION]: Uses a Python executor to generate positioning maps. The Python code is a static Matplotlib script embedded directly in the skill's instructions for visualization purposes.
[DATA_EXFILTRATION]: Performs web research and data extraction from competitor websites and review platforms. This is the primary intended functionality of the skill and does not involve exfiltration of sensitive user data.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process content from external websites (competitor pages and reviews), which constitutes an indirect prompt injection surface.
Ingestion points: External website content via tavily/search-assistant, infsh/agent-browser, and tavily/extract (SKILL.md)
Boundary markers: No explicit delimiters or instructions to ignore embedded commands are used when processing external content
Capability inventory: Subprocess execution via infsh, Python execution via infsh/python-executor, and image processing (SKILL.md)
Sanitization: No sanitization or validation of the fetched external content is performed before processing

competitor-teardown