answering-research-questions
Warn
Audited by Snyk on Jul 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: 0.85). The skill’s runtime workflow calls
rp_search/rp_fulltext/rp_cite, which fetch and ingest outsider-authored scholarly content (e.g., OpenAlex abstracts and OA full text/PDF text from third-party publishers) into the agent’s LLM context for evaluation/synthesis.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata