search

Pass

Audited by Gen Agent Trust Hub on Mar 20, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a legitimate integration with the Bright Data SERP API for searching Google.
  • [EXTERNAL_DOWNLOADS]: Communicates with the official Bright Data API endpoint at api.brightdata.com to retrieve search results.
  • [CREDENTIALS_UNSAFE]: API credentials are managed securely via environment variables (BRIGHTDATA_API_KEY), which is the recommended practice for avoiding credential exposure.
  • [SAFE]: Evaluated for indirect prompt injection risk:
  • Ingestion points: Untrusted content from external Google search results is loaded in scripts/search.sh.
  • Boundary markers: Data is handled in a structured JSON format.
  • Capability inventory: The script is limited to fetching and formatting data for output; it lacks dangerous capabilities such as code execution or system modification.
  • Sanitization: Employs the jq utility to strictly select and format only the specific data fields required.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 20, 2026, 12:37 PM