The Agent Skills Directory

[SAFE]: The skill follows secure practices for a research agent, including checking for local context files and organizing data in a structured, timestamped directory.
[PROMPT_INJECTION]: As a web-scraping skill, it naturally processes untrusted data from external URLs. While this creates a surface for indirect prompt injection, it is a standard characteristic of the research task and no malicious patterns are present.
[EXTERNAL_DOWNLOADS]: The skill communicates with external APIs for web scraping and SEO metrics. These are legitimate, well-known services required for the skill's functionality.
[COMMAND_EXECUTION]: The skill creates and writes to local markdown and JSON files to store research results. These file operations are restricted to the project's 'competitor-profiles' directory and are consistent with the skill's stated purpose.

competitor-profiling