academic-paper

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill's Phase 1 "Literature search" (literature_strategist_agent) and the Citation Compliance workflow explicitly require DOI/WebSearch verification and external checks (e.g., cross-referencing the Retraction Watch site), so the agents ingest and act on open/public third‑party web content which can materially change citation, drafting, and review decisions.

MEDIUM W021: Hidden or invisible Unicode characters detected (potential obfuscation or prompt injection).

• Hidden Unicode characters detected (1 type(s) found)