The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external ecommerce pages, marketplace listings, and crawl evidence, which could contain malicious instructions meant to subvert the agent's behavior.
Ingestion points: Data is collected from URLs, page content, and supplied marketplace evidence as described in SKILL.md.
Boundary markers: There are no specific instructions or delimiters provided to isolate external content or warn the agent to ignore embedded instructions (absent).
Capability inventory: The skill is restricted to diagnostic analysis and report generation in markdown; it does not have access to command execution or network-based exfiltration tools.
Sanitization: No sanitization or validation logic for external inputs is mentioned in the skill instructions (absent).
[EXTERNAL_DOWNLOADS]: The skill's documentation includes a command to install a package (nexscope-ai/ecommerce-seo-geo-skills) via npx. This is a standard installation step that fetches the skill from the vendor's repository.

ecommerce-geo-auditor