CVE-2026-48116
AnythingLLM: RCE via ripgrep --pre argument injection in filesystem-search-files agent skill
- State
- Published
- Severity
- 7.5 High
- Published
- May 28, 2026
- Updated
- May 30, 2026
- Reserved
- May 20, 2026
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.
Scores
| CVSS | Score | Vector | Source |
|---|---|---|---|
| 3.1 | 7.5 High | CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:H/I:H/A:H | GitHub_M |
Weaknesses
Affected Products
| Product | Versions |
|---|---|
anything-llmMintplex-Labs |
|
References
Every record here comes from the CVE Program’s CVE List. © 1999–2026 The MITRE Corporation. CVE is a registered trademark of The MITRE Corporation. The records are reproduced under the CVE Program terms of use.