scientific-deep-research
Warn
Audited by Snyk on Jul 15, 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 a runtime “Search” phase that fetches and evaluates academic sources via public web/DB lookups (e.g., Google Scholar/arXiv/Semantic Scholar and fallback to Wayback/Archive.today), which would ingest outsider-authored free text from those pages/papers into the agent’s LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata