CVE-2026-82280

HighCVSS 7.1

Published: 28/08/2026(UTC)Translated: 29/08/2026(UTC)NVD NIST

Exploitation Probability (EPSS)

Low risk

0.20%

10th percentile - higher than 10% of all known CVEs

Summary

Quivr through 0.0.322 fails to validate ownership in prompt endpoints, allowing authenticated users to modify any prompt by identifier. Attackers with read-only access to shared brains can read exposed prompt identifiers and overwrite system prompts affecting all brain users.

Risk Assessment

The risk includes unauthorized modification of system prompts, potentially leading to application behavior manipulation and potential data leakage or privilege escalation.

Recommendation

Update Quivr to a patched version and implement prompt ownership validation. Also restrict access to prompt endpoints.

Other vulnerabilities in Quivr

CVE-2026-82284High
Quivr versions through 0.0.322 fail to validate chat ownership in the GET /chat/{chat_id}/history, DELETE /chat/{chat_id}, and POST /chat/{chat_id}/question/answer endpoints. Authenticated attackers can read other users' conversation histories including private knowledge base content, delete arbitrary chats, and inject fabricated messages into other users' conversations.

Original NVD description (English source)