topic-monitor

Warn

Audited by Snyk on Feb 14, 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). Yes — scripts/monitor.py (search_topic) uses web-search-plus or other web search APIs to fetch arbitrary open-web results (title/snippet/url/content) which are then read and scored by importance_scorer and included in alerts/digest.py, meaning the agent ingests untrusted public/user-generated content from arbitrary URLs.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 14, 2026, 03:53 PM