obsidian-wiki
Warn
Audited by Snyk on Apr 16, 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). Flagged because the skill's workflow explicitly performs "联网搜索(必须)" (Step 2a) to fetch and ingest external search results ("提取 10 篇相关结果的标题、链接、摘要") and repeatedly states "联网搜索该概念最新进展" and "结合联网信息补充" (health checks and QA), meaning the agent reads and acts on untrusted public web content that can directly influence how it updates or creates wiki content.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata