search

Warn

Audited by Snyk on Feb 16, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.90). The scripts/search.sh builds a Google search URL and sends it to Bright Data's API (format "raw", data_format "parsed_light") then parses and outputs the .organic results (link, title, description), which exposes the agent to arbitrary public web content and user-generated pages that could carry indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 01:37 PM