The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The documentation references the vendor's official GitHub repository (AlpacaLabsLLC/skills-for-architects) for installation and symlinking. This is a legitimate source for the skill's components.
[COMMAND_EXECUTION]: The skill utilizes the Bash tool to perform local file operations, specifically for handling CSV files as part of the product enrichment workflow.
[PROMPT_INJECTION]: The skill is designed to ingest and process data from external, untrusted sources including CSV files, Google Sheets, and user-pasted text (SKILL.md, Step 1). This creates a surface for indirect prompt injection if the product names or descriptions contain malicious instructions.
Ingestion points: CSV file paths, Google Sheet IDs, and direct text input.
Boundary markers: The instructions do not explicitly provide delimiters or specific 'ignore instructions' warnings for the processed data, though it defines a strict schema for the output.
Capability inventory: The skill has capabilities to write to local files (Write, Edit) and update external spreadsheets (mcp__google__sheets_values_update).
Sanitization: No specific sanitization or validation of the input text content is defined beyond mapping to a schema. A preview step (Step 3) is included to allow human verification before changes are applied, which serves as a mitigation.

product-enrich