novelty-check
Warn
Audited by Snyk on Jun 22, 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 required workflow performs runtime web fetching (“WebFetch the abstract… and for the 1–2 closest, fetch the full text (PDF / NBER WP / SSRN / VoxEU / replication page)”), which can ingest outsider-authored free text from public web pages/PDFs into the agent’s LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata