Vulnerability · Published Aug 11, 2026 · Assigned by VulnCheck

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

Critical 9.6

In plain English

A critical-severity code injection in papersgpt-for-zotero from papersgpt. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 0.6% (higher than 47% of all known vulnerabilities).

Severity (CVSS 3.1)9.6Critical

Exploit odds (30 days)0.6%top 53.3% of all CVEs

Exploited in the wildNo reportsCISA SSVC: poc

Attack toolingNoneno public tooling known

Official 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.

Affected products (as reported)

Vendor	Product	Versions
papersgpt	papersgpt-for-zotero	0 – through 0.6.1

Weakness: CWE-94 · Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H

References

Product Repository product
GitHub Issue issue-tracking
Patch Commit patch
Pull Request technical-description
https://www.vulncheck.com/advisories/papersgpt-for-zotero-rce-via-unsanitized-llm-response-eval third-party-advisory