The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes data provided from external sources, specifically Amazon Brand Analytics report exports. This creates a potential surface for instructions hidden within the business data, though no dangerous capabilities are present to exploit such an injection.
Ingestion points: Search Frequency Rank exports, Market Basket Analysis reports, and Item Comparison reports as specified in the 'Workflow' section of SKILL.md.
Boundary markers: The instructions do not define clear delimiters or 'ignore' instructions to isolate the data being analyzed from the agent's instructions.
Capability inventory: The skill is limited to generating strategic text reports and recommendations; it does not request or use capabilities for network operations, file writing, or command execution.
Sanitization: No specific sanitization or validation of the provided data is mentioned in the instructions.
[EXTERNAL_DOWNLOADS]: The skill references an installation command using npx to fetch a repository from the vendor's GitHub account (nexscope-ai/Amazon-Skills). This resource belongs to the identified skill author and represents standard installation and integration practices for this vendor's ecosystem.

amazon-brand-analytics