Auth bypass in Danny-Avila Librechat
CVE-2026-44654
LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. In versions up to and including 0.8.3, a shared-agent editor can delete file records through `DELETE /api/files` that the owner has reused across multiple agents. The deletion removes the file globally — not just from the shared agent — breaking the owner's other private agents that reference the same `file_id`. The private agent retains a stale `file_id` reference that no longer resolves. A shared-agent editor can destroy files that the owner uses across multiple agents. The owner's private agents — which the attacker has no access to — break silently with stale `file_id` references. This is a cross-agent integrity violation: editing access to one agent should not affect another. Version 0.8.4 contains a patch.
Vulnerability class: Broken Access Control
EPSS: 0.003 (18.2th percentile) — read the EPSS interpretation.
CVSS v3 metric
CVSS v3 base score 8.1 (High). Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:H/A:H.
Affected products
- Danny-avila Librechat — versions < 0.8.5
- Librechat
Weakness classification (CWE)
References
- security-advisories@github.com (x_refsource_CONFIRM, Exploit, Vendor Advisory)
Frequently asked questions
- What is CVE-2026-44654?
- CVE-2026-44654 is a high-severity vulnerability in Danny-Avila Librechat, classified under Incorrect Authorization. CVSS score: 8.1/10. Published 2026-06-02.
- How severe is CVE-2026-44654?
- High severity. CVSS v3 base score is 8.1 out of 10.