The Agent Skills Directory

[COMMAND_EXECUTION]: The skill requires executing the zoodata.py Python script to perform API operations and handle data processing. It also specifies shell commands for creating temporary working directories in /tmp when executing the review analysis fallback chain.
[EXTERNAL_DOWNLOADS]: The skill makes network requests to api.zoodata.ai to retrieve Amazon product details, market benchmarks, and competitor analysis. This traffic is directed to the vendor's official API infrastructure and is required for the skill's primary functionality.
[PROMPT_INJECTION]: The skill ingests external data in the form of Amazon product reviews, which constitutes an indirect prompt injection surface. The workflow includes prompt templates that use delimiters to isolate this untrusted content and instructions for the agent to perform structured extraction, which mitigates the risk of the agent executing instructions embedded in the review data.

amazon-listing-audit-pro