The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The skill provides instructions to download and execute an installation script for the Bright Data CLI via curl -fsSL https://cli.brightdata.com/install.sh | bash. This script is hosted on the official domain of a well-known technology service provider.
[COMMAND_EXECUTION]: The workflow relies on the bdata CLI tool and shell utilities such as jq and xargs for data processing. This involves interpolating user-provided or scraped variables (e.g., URLs and company names) into shell commands, which requires the agent to properly manage inputs to prevent local command injection.
[PROMPT_INJECTION]: The skill's primary function is to ingest and synthesize untrusted data from the web, creating a surface for indirect prompt injection. * Ingestion points: Scraped data from competitor websites, third-party review platforms (G2, Capterra), and job listings entering the agent context via bdata scrape and bdata pipelines. * Boundary markers: None specified; the skill does not instruct the agent to use delimiters or ignore instructions within the retrieved data. * Capability inventory: The agent has access to web scraping tools, JSON processing utilities, and search functionality. * Sanitization: There is no mention of sanitizing or validating external content before it is analyzed.

competitive-intel