The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection via the processing of external marketplace data.
Ingestion points: Product attributes (such as titles and brand names) are fetched from the LinkFox tool gateway API as defined in references/api.md and processed by scripts/mpstats_ozon_seller_products.py.
Boundary markers: SKILL.md lacks explicit boundary markers or instructions to the agent to disregard potential commands embedded within the product data displayed in the summary table.
Capability inventory: The skill has network access capabilities via the provided Python script and interacts with the broader LinkFox agent ecosystem.
Sanitization: There is no logic present in the skill's scripts or instructions to sanitize or escape product data before it enters the agent's context.
[DATA_EXFILTRATION]: The skill performs network requests to the vendor's official infrastructure.
It connects to tool-gateway.linkfox.com to retrieve market statistics and skill-api.linkfox.com for operational feedback.
Credentials for these services are managed through the LINKFOXAGENT_API_KEY environment variable, which is consistent with secure development standards.

linkfox-mpstats-ozon-seller-products