highCVSS 7.5NVD status: Modified

CVE-2026-48116

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

ComponentAnythingLLM
Severityhigh (CVSS 7.5)
CVSS vectorCVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:H/I:H/A:H
Published (NVD)2026-05-28
Last modified2026-07-21
Affected versions
anythingllm < 1.13.0
Fixed in1.13.0
WeaknessCWE-77CWE-88
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. Prior to 1.13.0, the filesystem-search-files agent skill passes its LLM-controlled pattern parameter to ripgrep as a positional argument without a -- end-of-options separator. ripgrep parses any argument that starts with - as an option, so a pattern of --pre=/bin/sh turns ripgrep into a script executor: it runs /bin/sh <file> for every file it walks. An attacker who can chat with an agent on a deployment with the filesystem plugin enabled (the default in the official Docker image) can use this, together with the sibling filesystem-write-text-file skill, to run arbitrary commands inside the AnythingLLM server container. This vulnerability is fixed in 1.13.0.

Does CVE-2026-48116 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 1.13.0 or later.
  • Do not expose the component's API or UI to the internet without authentication in front of it.

Sources

Other AnythingLLM CVEs

All AnythingLLM CVEs