status

Warn

Audited by Snyk on May 12, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 1.00). The skill explicitly instructs agents to fetch and read arbitrary web pages (via WebFetch and Chrome navigation) as part of the Map Phase ("網頁抓取策略" in map-phase.md and related Map Phase instructions), so untrusted public web content is ingested at runtime and can materially influence agent decisions and tool use.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 12, 2026, 04:06 AM
Issues
1