highCVSS 7.5NVD status: Analyzed

CVE-2026-24477

AnythingLLM is an application that turns pieces of content into context that any LLM can use as references during chatting.

ComponentAnythingLLM, Qdrant
Severityhigh (CVSS 7.5)
CVSS vectorCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N
Published (NVD)2026-01-27
Last modified2026-06-17
Affected versions
anythingllm < 1.10.0
Fixed in1.10.0
WeaknessCWE-201
CISA KEVnot listed

NVD description

AnythingLLM is an application that turns pieces of content into context that any LLM can use as references during chatting. If AnythingLLM prior to version 1.10.0 is configured to use Qdrant as the vector database with an API key, this QdrantApiKey could be exposed in plain text to unauthenticated users via the `/api/setup-complete` endpoint. Leakage of QdrantApiKey allows an unauthenticated attacker full read/write access to the Qdrant vector database instance used by AnythingLLM. Since Qdrant often stores the core knowledge base for RAG in AnythingLLM, this can lead to complete compromise of the semantic search / retrieval functionality and indirect leakage of confidential uploaded documents. Version 1.10.0 patches the issue.

Does CVE-2026-24477 hit the version you run?Paste your docker-compose.yml, requirements.txt or package.json. The scanner checks your pinned versions against this CVE and every other one we track for AnythingLLM.
Check my stack

What to do

  • Upgrade AnythingLLM to 1.10.0 or later.
  • Do not expose the component's API or UI to the internet without authentication in front of it.

Sources

Read more

Other AnythingLLM CVEs

All AnythingLLM CVEs