google-search
Warn
Audited by Snyk on Mar 10, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). This skill's core tool ('google_search') calls Google's Custom Search API (https://www.googleapis.com/customsearch/v1) via the OneKey Agent Router (see SKILL.md and scripts/google_search.py), returning arbitrary public web search results that the agent would read and could materially influence its subsequent actions.
Audit Metadata