norikae-guide
Warn
Audited by Snyk on Mar 6, 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 skill explicitly fetches and extracts live pages from Yahoo! 乗換案内 (https://transit.yahoo.co.jp/search/result) as part of its required workflow (see SKILL.md step 3 and scripts/fetch_norikae_routes.py), so the agent reads untrusted third‑party web content that directly influences routing outputs and decisions.
Audit Metadata