webnovel-init
Warn
Audited by Snyk on Apr 30, 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's SKILL.md tool strategy and external-retrieval rules explicitly allow and require WebSearch/WebFetch (see "工具策略" and "外部检索触发条件" in SKILL.md) and the market-positioning reference ("必须先用 WebSearch/WebFetch 校验当期平台规则与榜单信号") which instructs the agent to fetch and interpret public platform pages/market data — untrusted third-party content that can materially influence decisions and subsequent tool use.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata