academic-paper
Warn
Audited by Snyk on May 20, 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's required Phase 1 "Literature search" (SKILL.md: "RESEARCH -> Search Strategy + Source Corpus") and the Citation Compliance agent (agents/citation_compliance_agent.md) explicitly describe verifying DOIs/URLs and cross-referencing public databases (e.g., Retraction Watch) and performing WebSearch/URL checks, which means the agents fetch and ingest open/public third‑party web content that the pipeline reads and uses to drive drafting, citation corrections, and review decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata