article-tech-write
Warn
Audited by Snyk on May 2, 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 workflow explicitly requires ingesting news materials and, if user-provided items are insufficient, to "主动搜索补充" (actively search and supplement) and uses remote image URLs ("图片:使用远程 URL"), meaning it fetches and reads public/untrusted web content (as shown in SKILL.md stage1 and the demo's external CDN image links) which the agent then interprets to drive article composition.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata