CVE-2026-48116 Details
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.
A vulnerability in AnythingLLM versions prior to 1.13.0 allows for remote code execution through improper handling of command-line arguments in the filesystem-search-files agent skill. The issue arises because the skill passes user-controlled pattern parameters to ripgrep without a proper separator, enabling the execution of arbitrary commands on the AnythingLLM server container. This vulnerability is exploitable by any authenticated user with access to an agent in a workspace where the filesystem plugin is enabled, which is the default in the official Docker image.
Users can update to AnythingLLM version 1.13.0 or later, where this vulnerability has been fixed.
Metrics
CVSS 4.0 Severity and Vector Strings:
No CVSS 4.0 data is available for this CVE.
CVSS 3.x Severity and Vector Strings:
No data available for CVSS Version 2.0 on this CVE.
CISA-ADP
Assessed May 30, 2026References to Advisories, Solutions, and Tools
By selecting these links, you will be leaving this site. These are references gathered from the official CVE record and are not endorsed by Volerion.
| URL | Source(s) | Tag(s) |
|---|---|---|
| https://github.com/Mintplex-Labs/anything-llm/security/advisories/GHSA-6hrp-7mw6-8v59 | CISA-ADP | ExploitMitigationVendor Advisory |
| https://github.com/Mintplex-Labs/anything-llm/commit/94ed62d320df1a06c229e4bc3ee09c2cb5111b33 | [email protected] | Patch |
| https://github.com/Mintplex-Labs/anything-llm/security/advisories/GHSA-6hrp-7mw6-8v59 | [email protected] | ExploitMitigationVendor Advisory |
Weakness Enumeration
| CWE-ID | CWE Name | Source |
|---|---|---|
| CWE-77 | Improper Neutralization of Special Elements used in a Command ('Command Injection') | [email protected] |
| CWE-88 | Improper Neutralization of Argument Delimiters in a Command ('Argument Injection') | [email protected] |
Affected Products
| Product | Versions |
|---|---|
| mintplexlabs anythingllm | < 1.13.0 |
CPE
Remediation
| |
Change History
6 change records found show changes
| Date | Action | Recorded By |
|---|---|---|
| Jul 21, 2026 | CVE Translated | [email protected] |
| Jun 17, 2026 | CVE Modified | [email protected] |
| Jun 17, 2026 | CVE Modified | CISA-ADP |
| May 30, 2026 | CVE Modified | CISA-ADP |
| May 29, 2026 | Initial Analysis | [email protected] |
| May 28, 2026 | New CVE Received | [email protected] |