The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill interacts with official vendor endpoints at tool-gateway.linkfox.com, api.linkfox.com, and agent-api.linkfox.com for data retrieval and account management. These are established service domains for the skill author.
[COMMAND_EXECUTION]: The skill uses Python scripts to perform API calls and local file operations. Command execution is limited to these provided scripts and standard system utilities like jq for data processing.
[DATA_EXFILTRATION]: Data exfiltration analysis shows that while the skill communicates with external APIs, it only sends necessary query parameters (keywords, SKUs) and authentication tokens to official vendor servers. Sensitive user data from the local environment is not accessed or transmitted.
[CREDENTIALS_UNSAFE]: The skill follows secure credential management practices. It instructs users to store API keys in environment variables (LINKFOX_AGENT_API_KEY) rather than hardcoding them. The onboarding.py script facilitates secure key acquisition through multi-factor authentication (SMS).
[SAFE]: Data storage is handled responsibly, writing responses to a dedicated linkfox directory within the project workspace rather than sensitive system locations or temporary directories. A 24-hour local caching mechanism is implemented to minimize redundant network calls.

linkfox-mpstats-ozon-product-search