price-comparison

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFEREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill documentation provides a command to install the required CLI tool by downloading a shell script from https://cli.brightdata.com/install.sh and piping it directly into bash. This script is hosted on the official domain of the skill author.
  • [COMMAND_EXECUTION]: The skill relies on executing the bdata command-line utility for its core functionality, including searching for products and collecting structured data from retail websites.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8).
  • Ingestion points: The agent retrieves untrusted data from multiple external retail sites via bdata scrape and bdata pipelines (SKILL.md).
  • Boundary markers: No explicit delimiters or safety instructions are defined to separate the scraped data from the agent's internal instructions.
  • Capability inventory: The skill executes shell commands through the bdata CLI across multiple retailers (SKILL.md).
  • Sanitization: No validation or sanitization processes are mentioned for the content retrieved from external sources before it is parsed and analyzed.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 05:55 AM
Security Audit — agent-trust-hub — price-comparison