nsfc-writer

Warn

Audited by Snyk on Mar 27, 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 ingests and acts on open web and scholarly sources (e.g., "使用 WebSearch 查找最新研究热点" and "文献调研集成: 使用已配置的 MCP 工具(PubMed、学术搜索引擎)" in SKILL.md, plus .github/copilot-instructions.md describing PubMed/Europe PMC/CORE unified_search), and it requires the agent to read and incorporate those third‑party results into writing, citations, and decision-making, which could allow indirect prompt injection from untrusted public content.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 27, 2026, 04:05 PM
Issues
1