The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The installation instructions include fetching and executing a shell script from the vendor's official domain: curl -fsSL https://cli.brightdata.com/install.sh | bash. This is a standard installation method provided by the author.
[EXTERNAL_DOWNLOADS]: The skill recommends installing the @brightdata/cli package via the npm registry for standard cross-platform installation.
[COMMAND_EXECUTION]: The skill's functionality is centered around executing bdata and brightdata shell commands to interact with the vendor's web data platform.
[PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it ingests untrusted data from the web.
Ingestion points: bdata scrape, bdata search, and bdata pipelines commands fetch external content from arbitrary URLs into the agent context.
Boundary markers: The instructions do not define specific markers or delimiters to isolate scraped content from agent instructions.
Capability inventory: The skill utilizes shell command execution and file system writes (-o flag) to handle data.
Sanitization: There is no evidence of content sanitization or filtering for the data retrieved from external URLs before it is processed by the agent.

brightdata-cli