ai-search

Warn

Audited by Snyk on Nov 17, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (medium risk: 0.30). The Local branch has the agent capture Ask Maps and the listing's AI summary, which are generated from Google profile reviews that any outsider can post, without the agent selecting a specific review, so this exposure is medium under recall-first; the core web-search and fetch steps (Google AI Overviews, retrieval proxy, winning-page fetches) are low on their own.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Nov 17, 2026, 04:23 PM
Issues
1