The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses shell scripts (scripts/datasets.sh and scripts/fetch.sh) to interact with the Bright Data API. It uses jq to safely construct JSON payloads from user-provided arguments, mitigating standard command injection risks when building the API request body. However, as with any skill executing shell commands, the agent has the capability to run these scripts with arbitrary arguments provided by the user.
[DATA_EXFILTRATION]: The skill interacts with the external domain api.brightdata.com to send URLs for scraping and retrieve structured data. This is the primary intended function of the skill. While it sends user-provided URLs to a third-party service, this behavior is transparently documented and is the core purpose of the tool. The skill handles the BRIGHTDATA_API_KEY via an environment variable, which is a standard and recommended security practice for managing secrets in such environments.

data-feeds