aris-semantic-scholar
Warn
Audited by Snyk on May 6, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill directly queries the public Semantic Scholar API (https://api.semanticscholar.org/graph/v1 and related openAccessPdf/DOI URLs) per the SKILL.md search/fetch workflow (Steps 2, 3, 5, 6) and ingests abstracts, TLDRs, citation counts and PDF links which the agent uses to rank, filter, and decide follow-up actions, exposing it to untrusted third-party content that could carry indirect prompt injection.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata