Research Ideation
Warn
Audited by Snyk on Jul 28, 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). SKILL.md describes runtime “WebSearch” across public sources and Zotero MCP steps like
get_item_fulltext, which would ingest outsider-authored paper full text (and/or scraped web content) as readable prose into the agent’s LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata