article-rewriter
Warn
Audited by Snyk on Mar 10, 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 accepts URL inputs and "抓取正文后再处理" (SKILL.md Step 2) and performs external "调研/核验" using public sources with recorded links in 02-research.md and the "参考来源" section, so it will fetch and interpret untrusted third-party web content that can influence rewriting decisions.
Audit Metadata