bright-data-mcp

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill uses forceful imperative language, such as "MUST replace" and "ALWAYS use", to override default agent behavior and mandate the use of specific third-party tools over built-in platform capabilities like WebFetch and WebSearch.
  • [EXTERNAL_DOWNLOADS]: The instructions direct the user to connect to a remote server at mcp.brightdata.com and suggest installing the '@brightdata/mcp' package via NPM for local execution.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to fetch and process arbitrary data from untrusted websites, creating a large attack surface for indirect prompt injection where malicious instructions embedded in web pages could influence the agent.
  • Ingestion points: Content retrieved via 'scrape_as_markdown', 'search_engine', and various 'web_data_*' tools.
  • Boundary markers: The skill does not specify any delimiters or warnings to the agent to ignore instructions found within the scraped content.
  • Capability inventory: The skill enables extensive web interaction, including scraping, search, and browser automation (click, type, navigate).
  • Sanitization: No evidence of data sanitization or validation is provided in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 06:47 AM
Security Audit — agent-trust-hub — bright-data-mcp