The Agent Skills Directory

[SAFE]: The skill's primary function is data analysis and reporting. It does not attempt to execute system commands, persist on the host, or access sensitive user credentials.
[EXTERNAL_DOWNLOADS]: The skill utilizes the unifapi data service to access live search engine results (SERP) and web page content from mcp.unifapi.com. These are recognized vendor resources necessary for the skill's operation.
[PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests content from external websites. (1) Ingestion points: Fetches rendered web content and links using browser/html and browser/links tools as described in SKILL.md. (2) Boundary markers: The skill does not define specific delimiters to separate untrusted web content from its core instructions. (3) Capability inventory: The skill's capabilities are limited to reading data and generating markdown output; it lacks dangerous tools for file system manipulation or arbitrary command execution. (4) Sanitization: No explicit validation or sanitization of external web data is implemented in the workflow.

seo-fix-plan