Literature Research
Warn
Audited by Snyk on Jul 8, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.95). SKILL.md requires calling
alphaxiv.get_paper_content(fullText: true)andalphaxiv.answer_pdf_querieson arbitrary paper/PDF URLs at runtime, which ingests outsider-authored full paper text (public web/arXiv content) into the agent’s LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata