content-creator
Warn
Audited by Snyk on Apr 7, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The SKILL.md mandates a non-skippable "Step 4: 深度研究 (Research)" that explicitly includes "外部研究(网络搜索)" (searching the web for latest industry dynamics, data, and cases) and requires integrating those external research_notes.md into the article creation, which means the agent will fetch and interpret open/public third‑party (potentially user‑generated/untrusted) content that can influence subsequent actions and outputs.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata