CVE-2026-48116: CWE-77: Improper Neutralization of Special Elements used in a Command ('Command Injection') in Mintplex-Labs anything-llm
CVE-2026-48116 is a command injection vulnerability in Mintplex-Labs' anything-llm application versions prior to 1. 13. 0. The issue arises because the filesystem-search-files agent skill passes an LLM-controlled pattern parameter directly to ripgrep without using an end-of-options separator. This allows specially crafted patterns starting with '-' to be interpreted as ripgrep options, enabling execution of arbitrary shell commands. An attacker with access to chat with an agent on a deployment with the filesystem plugin enabled can exploit this to run commands inside the server container. The vulnerability is fixed in version 1. 13. 0.
AI Analysis
Technical Summary
The vulnerability in anything-llm before version 1.13.0 involves improper neutralization of special elements in a command (CWE-77). The filesystem-search-files agent skill passes an LLM-controlled pattern parameter to ripgrep as a positional argument without a '--' end-of-options separator. Since ripgrep treats arguments starting with '-' as options, an attacker can craft a pattern like '--pre=/bin/sh' to cause ripgrep to execute '/bin/sh <file>' for each file it processes. This enables command injection inside the server container when combined with the filesystem-write-text-file skill. The vulnerability has a CVSS 3.1 score of 7.5 (high severity) and is fixed in version 1.13.0.
Potential Impact
Successful exploitation allows an attacker who can interact with the agent on a vulnerable deployment to execute arbitrary commands inside the AnythingLLM server container. This can lead to full compromise of the container, including confidentiality, integrity, and availability impacts. The vulnerability affects deployments with the filesystem plugin enabled, which is the default in the official Docker image.
Mitigation Recommendations
Upgrade anything-llm to version 1.13.0 or later, where this vulnerability is fixed. Prior to upgrading, restrict access to the agent interface to trusted users only and disable the filesystem plugin if possible. Patch status is not explicitly stated but the vendor fixed the issue in version 1.13.0, so applying this official fix is the recommended remediation.
CVE-2026-48116: CWE-77: Improper Neutralization of Special Elements used in a Command ('Command Injection') in Mintplex-Labs anything-llm
Description
CVE-2026-48116 is a command injection vulnerability in Mintplex-Labs' anything-llm application versions prior to 1. 13. 0. The issue arises because the filesystem-search-files agent skill passes an LLM-controlled pattern parameter directly to ripgrep without using an end-of-options separator. This allows specially crafted patterns starting with '-' to be interpreted as ripgrep options, enabling execution of arbitrary shell commands. An attacker with access to chat with an agent on a deployment with the filesystem plugin enabled can exploit this to run commands inside the server container. The vulnerability is fixed in version 1. 13. 0.
CVSS v3.1
Score 7.5high
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
The vulnerability in anything-llm before version 1.13.0 involves improper neutralization of special elements in a command (CWE-77). The filesystem-search-files agent skill passes an LLM-controlled pattern parameter to ripgrep as a positional argument without a '--' end-of-options separator. Since ripgrep treats arguments starting with '-' as options, an attacker can craft a pattern like '--pre=/bin/sh' to cause ripgrep to execute '/bin/sh <file>' for each file it processes. This enables command injection inside the server container when combined with the filesystem-write-text-file skill. The vulnerability has a CVSS 3.1 score of 7.5 (high severity) and is fixed in version 1.13.0.
Potential Impact
Successful exploitation allows an attacker who can interact with the agent on a vulnerable deployment to execute arbitrary commands inside the AnythingLLM server container. This can lead to full compromise of the container, including confidentiality, integrity, and availability impacts. The vulnerability affects deployments with the filesystem plugin enabled, which is the default in the official Docker image.
Mitigation Recommendations
Upgrade anything-llm to version 1.13.0 or later, where this vulnerability is fixed. Prior to upgrading, restrict access to the agent interface to trusted users only and disable the filesystem plugin if possible. Patch status is not explicitly stated but the vendor fixed the issue in version 1.13.0, so applying this official fix is the recommended remediation.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- GitHub_M
- Date Reserved
- 2026-05-20T18:46:58.289Z
- Cvss Version
- 3.1
- State
- PUBLISHED
- Remediation Level
- null
Threat ID: 6a18b4aee29bf47b5032f471
Added to database: 5/28/2026, 9:33:34 PM
Last enriched: 5/28/2026, 9:48:26 PM
Last updated: 5/28/2026, 10:39:40 PM
Views: 4
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
Need more coverage?
Upgrade to Pro Console for AI refresh and higher limits.
For incident response and remediation, OffSeq services can help resolve threats faster.
Latest Threats
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.