peer-reviewer
Warn
Audited by Snyk on Mar 5, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The workflow explicitly retrieves and reads full texts from a Zotero library via the Zotero MCP in Phase 1 (e.g., mcp__zotero-mcp__zotero_get_item_fulltext) and then uses those third-party texts to build personas and drive review decisions, so external content can materially influence agent actions.
Audit Metadata