The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill connects to vendor-controlled domains including tool-gateway.linkfox.com, api.linkfox.com, and agent-api.linkfox.com to fetch analytics data and handle user authentication flows. These network operations are consistent with the skill's stated purpose.
[COMMAND_EXECUTION]: The skill employs Python scripts (seerfar_ozon_category_search.py and onboarding.py) to execute its core logic. These scripts are intended to be invoked by the agent to interact with the marketplace API and assist the user with API key configuration.
[INDIRECT_PROMPT_INJECTION]: The skill ingests product titles and descriptions from the Ozon marketplace via the Seerfar API. This untrusted data represents a potential attack surface if it contains instructions designed to influence the agent's behavior.
Ingestion points: External data is retrieved from the /seerfar/ozon/categorySearch endpoint in scripts/seerfar_ozon_category_search.py.
Boundary markers: There are no explicit delimiters or boundary markers used in the instructions to separate external data from agent commands.
Capability inventory: The skill possesses capabilities for network access (via urllib and requests) and local file writing (to the linkfox/ directory).
Sanitization: The skill outputs raw product data to the console and files without specialized sanitization to prevent the interpretation of embedded instructions.

linkfox-seerfar-ozon-category-search