UTC
High

Open WebUI has Knowledge Base Destruction and RAG Poisoning via Unauthorized Collection Overwrite

CVE-2026-44554 · GHSA-7r82-qhg4-6wvj · published 2026-05-08 · updated 2026-05-15

Severity
High
CVSS score
8.1
Chance of exploitation (EPSS)
0.29%
Fixed in
0.9.0
  • Exploitation No known exploitation
  • Automatable No
  • Technical impact Total
  • CISA SSVC
What it is

Data destruction: Victim's original KB embeddings are permanently deleted from the vector store RAG poisoning: Attacker-controlled content replaces legitimate knowledge, causing the LLM to return misleading or malicious answers to the victim Indirect prompt injection: Poisoned content can contain crafted prompts that manipulate the victim's LLM behavior when queried Persistence: The poisoned content persists until the KB is rebuilt from source files

What to do

Upgrade open-webui to 0.9.0 or later. If you start it from an MCP config with npx or uvx, pin that version so an old cached copy is not used.

Affected
PackageRegistryAffectedFixed in
open-webuiPyPI<= 0.8.120.9.0

The impact, patch and workaround text comes from the advisory, shortened (GitHub Advisory Database, CC BY 4.0). Proof-of-concept and reproduction sections and code are left out; the original advisory has them.

Sources: GitHub Advisory Database, reviewed and malware advisories (CC BY 4.0, https://github.com/advisories); advisories published by Cursor (https://github.com/cursor/cursor/security/advisories); advisories published by OpenClaw (https://github.com/openclaw/openclaw/security/advisories); advisories published by vLLM (https://github.com/vllm-project/vllm/security/advisories); advisories published by Open WebUI (https://github.com/open-webui/open-webui/security/advisories); advisories published by n8n (https://github.com/n8n-io/n8n/security/advisories); advisories published by Flowise (https://github.com/FlowiseAI/Flowise/security/advisories); advisories published by Langflow (https://github.com/langflow-ai/langflow/security/advisories); advisories published by the MCP Python SDK project (https://github.com/modelcontextprotocol/python-sdk/security/advisories); advisories published by MLflow (https://github.com/mlflow/mlflow/security/advisories); CISA Known Exploited Vulnerabilities catalog (CC0). Data as of 2026-11-22. ShieldMap describes how each problem works and how to fix it; it does not publish exploit code. Report a correction to [email protected].