harness-plan
Warn
Audited by Snyk on Mar 14, 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 create flow explicitly performs "技術調査（WebSearch）" (references/create.md Step 3) using WebSearch queries to fetch and use open-web content to inform Plans.md generation, meaning untrusted third-party pages could influence planning decisions and subsequent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata