New MCP server — Bring vulnerability intelligence into your AI
Back to feed

CVE-2026-48116

ExploitedNVDCIRCLENISA

EUVD-2026-33068 · Published May 28, 2026

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.

Technologies

Mintplexlabs Anythingllm

Weaknesses

CWE-88CWE-77

CVSS scores

  • v3.18.8CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

MITRE ATT&CK

Inferred

Where this vulnerability fits in an attack

Initial Access

References

Potentially impacted assets

See if this affects your attack surface

News

Our latest news

Couldn’t load the latest news.

Take 15 minutes to discover our platform with our experts

PatrowlIntel platform screenshot