paper-research-assistant
Warn
Audited by Snyk on Jun 24, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). 运行时会将用户提供的论文 PDF 文本（外部作者的内容）经
parse_paper.py的page.get_text()提取为可读字符串并写入paper_metadata.json，随后generate_report.py把metadata['abstract']/sections/key_formulas等字段拼接进 LLM上下文（报告生成）。
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata