building-screening-rubrics
Warn
Audited by Snyk on Jul 17, 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). Yes—during Phase 2/3 the workflow calls
rp_search/rp_abstractsto fetch outsider-authored paper abstracts from OpenAlex/Scopus at runtime, and those abstracts are then inserted into the agent’s LLM context for classification and rubric refinement.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata