CVE-2026-73032: PapersGPT for Zotero remote code execution via LLM endpoint response

Summary

PapersGPT for Zotero 0.6.1 (CVE-2026-73032) passes LLM endpoint output unsanitized to window.eval() in views.ts, letting an attacker run arbitrary JavaScript. Attackers can reach this through prompt injection in PDFs, MITM interception of API requests, or a malicious custom LLM endpoint. The code runs in Zotero's chrome-privileged context, enabling file read and write, process execution, and access to all Zotero data.

Mitigation

The source does not state a fix yet. Check the original advisory for updates.

Related items

• HighCVE-2026-63651: LiveDocs is a primary-source-first documentation for AI agents. Prior to version 0.7.0, fetch_docs and introspect…Similar attack · NVD/CVE Database
• HighCVE-2026-125271 - AWS API MCP Server Security Policy Bypass via Incorrect Operation Name NormalizationSimilar attack · AWS Security Bulletins
• MediumCVE-2026-83953 GitHub Copilot for Jetbrains Information Disclosure VulnerabilitySimilar attack · MSRC Security Update Guide
• HighGHSA-ghwv-vrp2-2975: Cocos AI Intra-handshake attested TLS implementation is vulnerable to TOCTOU AttacksSimilar attack · GitHub Advisory Database
• MediumGHSA-5m6c-38r8-5w76: Dagu MCP DAG specification read bypasses path containment and workspace isolationSimilar attack · GitHub Advisory Database