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.

Attack Vector Network

Attack Complexity Low

Privileges Required None

Attack Requirements None

User Interaction Active

Vulnerable System Confidentiality Impact High

Vulnerable System Integrity Impact High

Vulnerable System Availability Impact High

Subsequent System Confidentiality Impact High

Subsequent System Integrity Impact High

Subsequent System Availability Impact High

Attack Vector Network

Attack Complexity Low

Privileges Required None

Scope Changed

Confidentiality Impact High

Integrity Impact High

Availability Impact High

User Interaction Required

No CVSS v3.0

No CVSS v2

This CVE is not in the KEV list.

No EPSS score available.

Exploitation poc

Automatable no

Technical Impact total

Default status is the baseline for the product, each version can override it (e.g. patched versions marked unaffected).

Vendor Product Default status Versions
papersgpt papersgpt-for-zotero affected
Version Status Constraints
0 affected ≤ 0.6.1

No data.

No data.

No data.

Project Subscriptions

No data.

Advisories

No advisories yet.

Fixes

Solution

No solution given by the vendor.

Workaround

No workaround given by the vendor.

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

Tue, 11 Aug 2026 21:30:00 +0000

Type Values Removed Values Added
Metrics ssvc

{'options': {'Automatable': 'no', 'Exploitation': 'poc', 'Technical Impact': 'total'}, 'version': '2.0.3'}

Tue, 11 Aug 2026 19:30:00 +0000

Type Values Removed Values Added
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.
Title PapersGPT for Zotero 0.6.1 RCE via Unsanitized LLM Response eval()
Weaknesses CWE-94
References
Metrics cvssV3_1

{'score': 9.6, 'vector': 'CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H'}

cvssV4_0

{'score': 9.4, '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'}

Projects

Sign in to view the affected projects.

cve-icon MITRE

Status: PUBLISHED

Assigner: VulnCheck

Published:

Updated: 2026-08-11T20:07:45.320Z

Reserved: 2026-08-10T18:48:59.022Z

Link: CVE-2026-73032

cve-icon Vulnrichment

Updated: 2026-08-11T20:07:40.507Z

cve-icon NVD

Status : Received

Published: 2026-08-11T20:18:46.320

Modified: 2026-08-11T20:18:46.320

Link: CVE-2026-73032

cve-icon Redhat

No data.

cve-icon OpenCVE Enrichment

No data.

Weaknesses