The Agent Skills Directory

[SAFE]: The skill's instructions are strictly limited to performing market research and strategy consulting tasks. It follows a logical, professional methodology for data gathering and calculation.
[EXTERNAL_DOWNLOADS]: The skill fetches data from established and well-known services such as the SEC (filings), the World Bank, IMF, and reputable market research firms (e.g., Gartner, Statista) to support its calculations. These operations are essential to the skill's primary function and target trusted domains.
[INDIRECT_PROMPT_INJECTION]: The skill ingests data from external websites, which is a common surface for indirect prompt injection. However, the risk is minimal as the ingested data is used exclusively for generating a markdown report, and the instructions do not involve executing commands or code derived from the fetched content.
Ingestion points: External data is gathered via WebSearch and WebFetch from market research and competitor sites.
Boundary markers: No explicit delimiters are used to separate fetched content from the agent's instructions.
Capability inventory: The skill has access to tools including Bash, Write, Edit, Read, Glob, and Grep to manage file operations for report generation.
Sanitization: No explicit sanitization of fetched web content is performed.

market-sizing