article-writer
Warn
Audited by Snyk on Mar 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: 1.00). The skill's Step 1 ("搜索资料") explicitly requires using WebSearch to fetch and deeply summarize multi-source web content from the open web, which the agent will read and use to compose and decide article content, exposing it to untrusted third-party input.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata