The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests and processes untrusted data from external search results.
Ingestion points: The skill retrieves content from local/search, maps/search, seo/serp, and geo/serp endpoints via the unifapi tool to analyze competitor pages and rankings.
Boundary markers: The instructions lack specific boundary markers or "ignore embedded commands" warnings to encapsulate data retrieved from external web pages.
Capability inventory: The skill's primary focus is reporting and benchmark calculation. It does not contain capabilities for modifying local files, executing arbitrary code (eval/exec), or performing non-tool-mediated network operations.
Sanitization: No explicit sanitization or filtering of the text fetched from search engine results is described before the data is analyzed by the agent.
[EXTERNAL_DOWNLOADS]: The skill documentation references external dependencies and resources managed by the vendor.
Tool Dependency: The skill relies on the unifapi tool/skill for its core data retrieval functionality.
Installation Paths: The README provides instructions for installing plugins from the unifapi-agent/agents marketplace and references documentation hosted on the vendor's domain (unifapi.com).

practice-area-rank-audit