deep-research
Warn
Audited by Snyk on Jul 10, 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). This skill’s required workflow includes runtime literature retrieval from public scholarly sources/APIs (e.g., Crossref/Semantic Scholar/arXiv/DBLP) and then uses the retrieved paper content/metadata to write the survey, which can include outsider-authored free text that becomes LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata