The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes shell commands using the bdata CLI tool along with standard utilities like jq, xargs, and bash to automate data extraction pipelines and verify output integrity.
[EXTERNAL_DOWNLOADS]: The skill directs users to install and authenticate the Bright Data CLI (bdata), which is a vendor-provided tool required for the skill's primary functionality.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources (such as Amazon, LinkedIn, and TikTok), which presents a risk of indirect prompt injection.
Ingestion points: Data is retrieved from external URLs via bdata pipelines and stored in local JSON or NDJSON files (e.g., product.json, posts.ndjson) to be read by the agent.
Boundary markers: The instructions do not utilize specific delimiters or boundary markers to differentiate between extracted data and agent instructions.
Capability inventory: The skill performs shell command execution, file system writes, and network operations (via the CLI tool).
Sanitization: The skill incorporates verification steps using jq to ensure valid JSON structure and check for error fields, but it does not perform content-based sanitization of the extracted data.

data-feeds