skills/brightdata/skills/data-feeds/Gen Agent Trust Hub

data-feeds

Pass

Audited by Gen Agent Trust Hub on Oct 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external websites (such as Amazon, LinkedIn, and social media platforms) via the bdata CLI. This data is untrusted and could potentially contain malicious instructions intended to influence the agent's behavior.
  • Ingestion points: Data is retrieved via bdata pipelines and saved to JSON files (e.g., in SKILL.md and references/examples.md).
  • Boundary markers: No specific delimiters or "ignore" instructions are used when the agent processes the resulting JSON.
  • Capability inventory: The skill utilizes subprocess execution for the bdata CLI and jq for data manipulation.
  • Sanitization: No explicit sanitization or filtering of the content retrieved from external URLs is mentioned before the agent reads the output.
  • [COMMAND_EXECUTION]: The skill relies on shell command execution to interact with the Bright Data CLI and process data. It includes sophisticated patterns for parallel processing and verification.
  • Evidence: Extensive use of bdata, jq, xargs, and bash loops throughout the documentation and examples.
  • Safety: Examples demonstrate safe practices for passing arguments to subshells, such as using positional parameters with bash -c inside xargs blocks to prevent shell injection.
  • [EXTERNAL_DOWNLOADS]: The skill requires and guides the installation of the @brightdata/cli Node.js package. As the skill is authored by Bright Data, this is an expected dependency on the vendor's own official tooling.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 12, 2026, 11:26 PM