nature-academic-search
Warn
Audited by Snyk on Jun 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: 0.75). At runtime, the agent can call the MCP tool
search_papers(and related tools) which returns JSON containing free-text fields liketitle/abstractfetched from outsider-authored public sources (e.g., CrossRef/PubMed/arXiv), and those strings are then placed into the agent’s LLM context as part of the tool result.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata