PapersGPT for Zotero 0.6.1 RCE via Unsanitized LLM Response eval()
Published Aug 11, 2026
9.4
CRITICALCVSS 4.0
EPSS 0.56%
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
-
Affected
- ≥ 0, ≤ 0.6.1
Default status is the baseline for the product. Each version can override it (patched versions can be marked unaffected).
| Vendor | Product | Default status | Versions |
|---|---|---|---|
| Papersgpt | Papersgpt-for-Zotero | affected | Affected
|
No data.
No data.
No Red Hat product state for this CVE.
No package ranges for this CVE.
Remediation
No remediation recorded yet.
References (6)
- https://euvd.enisa.europa.eu/vulnerability/EUVD-2026-56896 Advisory
- https://github.com/papersgpt/papersgpt-for-zotero product
- https://github.com/papersgpt/papersgpt-for-zotero/commit/094134172ce4a344a31e4b196cc75d1806383658 patch
- https://github.com/papersgpt/papersgpt-for-zotero/issues/154 exploitissue-tracking
- https://github.com/papersgpt/papersgpt-for-zotero/pull/155 technical-description
- https://www.vulncheck.com/advisories/papersgpt-for-zotero-rce-via-unsanitized-llm-response-eval third-party-advisory
| Link | Providers | Tags |
|---|---|---|
| https://euvd.enisa.europa.eu/vulnerability/EUVD-2026-56896 | Advisory | |
| https://github.com/papersgpt/papersgpt-for-zotero | product | |
| https://github.com/papersgpt/papersgpt-for-zotero/commit/094134172ce4a344a31e4b196cc75d1806383658 | patch | |
| https://github.com/papersgpt/papersgpt-for-zotero/issues/154 | exploitissue-tracking | |
| https://github.com/papersgpt/papersgpt-for-zotero/pull/155 | technical-description | |
| https://www.vulncheck.com/advisories/papersgpt-for-zotero-rce-via-unsanitized-llm-response-eval | third-party-advisory |
Change history (0)
No recorded changes yet.
CVE.org / MITRE
CISA Vulnrichment
Red Hat
No data
GitHub
No data