explore-sota
Warn
Audited by Snyk on Jun 18, 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). The skill’s runtime workflow uses MCP scholarly sources (e.g., arXiv/semantic-scholar/openalex) to fetch paper metadata and citation/reference lists, which are outsider-authored text ingested via those APIs into the agent’s context for triage/digestion.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata