The Agent Skills Directory

[COMMAND_EXECUTION]: The skill operates by running local Python scripts, scripts/echotik_list_new_product_rank.py and scripts/onboarding.py, which are used to interface with the EchoTik API and handle user authentication tasks.
[EXTERNAL_DOWNLOADS]: The scripts/onboarding.py script relies on and suggests the installation of well-known, legitimate Python packages including requests, qrcode, and pillow to enable its core functionality.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from the external EchoTik API, which introduces a theoretical surface for indirect prompt injection if retrieved product names or metadata contain adversarial instructions.
Ingestion points: Data enters the environment via the /echotik/listNewProductRank API endpoint as handled in scripts/echotik_list_new_product_rank.py.
Boundary markers: There are no explicit delimiters or boundary instructions implemented in the script to separate external content from the agent's logic.
Capability inventory: The skill scripts are capable of executing local commands, writing to a linkfox subdirectory within the project, and initiating network requests to the vendor's API domains.
Sanitization: The skill does not perform specific validation or sanitization of the remote API response before presenting it to the agent context.

linkfox-echotik-list-new-product-rank