CVE-2026-58473
CriticalCVSS 9.1Exploitation Probability (EPSS)
Low risk42th percentile - higher than 42% of all known CVEs
Summary
Cognee before version 1.2.0 contains an improper access control vulnerability that allows unauthenticated attackers to overwrite the global LLM provider configuration by self-registering an account and calling the settings endpoint, which performs no admin or superuser check. Attackers can redirect all LLM operations instance-wide to an attacker-controlled endpoint by exploiting the process-wide singleton configuration cache, enabling exfiltration of prompts, uploaded documents, extracted entities, and knowledge graph content from all users.
Risk Assessment
The risk for the organization includes complete loss of confidentiality of data processed by the Cognee system, including sensitive prompts, documents, and domain knowledge, as well as the possibility of manipulation of LLM model results by the attacker.
Recommendation
Immediately upgrade Cognee to version 1.2.0 or later, which contains a fix for this vulnerability. Until the update is applied, restrict access to the settings endpoint to trusted administrators only.
Other vulnerabilities in Cognee
See all- CVE-2026-31231Critical
Cognee up to version 0.4.0 contains a critical remote code execution vulnerability in its notebook cell execution API endpoint. The endpoint executes arbitrary Python code provided by the user using the unsafe exec() function without any sandboxing, validation, or security controls.
- CVE-2026-105141Medium
A security flaw has been discovered in topoteretes cognee up to 1.5.4 in the get_user_id_by_email function of cognee/modules/users/authentication/get_api_auth_backend.py, part of the JWT Signing Key Handler component. Manipulation of the FASTAPI_USERS_JWT_SECRET argument results in hard-coded credentials. The attack can be launched remotely.
Original NVD description (English source)
Cognee before 1.2.0 contains an improper access control vulnerability that allows unauthenticated attackers to overwrite the global LLM provider configuration by self-registering an account and calling the settings endpoint, which performs no admin or superuser check. Attackers can redirect all LLM operations instance-wide to an attacker-controlled endpoint by exploiting the process-wide singleton configuration cache, enabling exfiltration of prompts, uploaded documents, extracted entities, and knowledge graph content from all users.
Vulnerability data from NVD (NIST) · CISA KEV · EPSS