The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process product-specific data, such as ASINs and listing descriptions, which provides a standard surface for indirect prompt injection.
Ingestion points: Processes user-provided product details, listing content, and keyword data as defined in the 'Usage Examples' and 'Output Format' sections of SKILL.md.
Boundary markers: No specific delimiters or instructions to ignore embedded commands in the input data are defined in the instructions.
Capability inventory: The skill is composed entirely of markdown instructions and does not possess capabilities for subprocess execution, file system modification, or automated network requests.
Sanitization: The skill does not implement explicit sanitization or validation of external input data.
[EXTERNAL_DOWNLOADS]: The skill provides installation instructions that reference a remote repository hosted by the vendor.
Evidence: The installation command npx skills add nexscope-ai/Amazon-Skills points to the nexscope-ai vendor repository on GitHub.
[NO_CODE]: The provided skill consists exclusively of markdown documentation and configuration without any accompanying scripts or executable logic.

amazon-search-optimization