The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes untrusted external data, such as competitor listings and product details fetched from Amazon. This represents an indirect prompt injection surface; however, the risk is mitigated by the script's tokenization and lexical cleaning logic, which transforms raw text into structured keyword data before it is presented back to the AI agent.
[DATA_EXFILTRATION]: Network communication is limited to the authorized vendor's infrastructure using the NEXSCOPE_PROXY_BASE environment variable. The skill correctly manages sensitive credentials by accessing the NEXSCOPE_API_KEY through the environment rather than hardcoding it.
[COMMAND_EXECUTION]: The skill utilizes local Python scripts (listing_keyword_optimizer.py and ecommerce_chart_helpers.py) for data processing and chart generation. These scripts use standard, well-known libraries and do not attempt to gain elevated privileges or access sensitive system directories.

listing-keyword-optimizer