Vulnerability · Published May 28, 2026 · Assigned by GitHub_M
CVE-2026-48116AnythingLLM: RCE via ripgrep --pre argument injection in filesystem-search-files agent skill
High 7.5
In plain English
A high-severity command injection in anything-llm from Mintplex-Labs. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 0.4% (higher than 31% of all known vulnerabilities).
Official 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.
Affected products (as reported)
| Vendor | Product | Versions |
|---|---|---|
| Mintplex-Labs | anything-llm | < 1.13.0 |
Weakness: CWE-77, CWE-88 · Vector: CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:H/I:H/A:H