CVE-2026-19282
Received Received - Intake

Command Injection in llm_memory_mcp

Publication date: 2026-08-08

Last updated on: 2026-08-08

Assigner: VulDB

Description
A weakness has been identified in andreahaku llm_memory_mcp up to f11dc8bcff3ff8cf943a2945f99ff3b0bdc8a6d0. This impacts the function auto.capture of the file src/autolearn/GitHooksManager.ts of the component llm_memory_mcp. Executing a manipulation of the argument hash can lead to command injection. The attack is restricted to local execution. This product does not use versioning. This is why information about affected and unaffected releases are unavailable. The project was informed of the problem early through an issue report but has not responded yet.

CVSS Scores

EPSS Scores

Probability:
Percentile:

Meta Information

Published
2026-08-08
Last Modified
2026-08-08
Generated
2026-08-08
AI Q&A
2026-08-08
EPSS Evaluated
N/A
NVD
CVE-2026-19282
EUVD
EUVD-2026-54781

Affected Vendors & Products

Showing 1 associated CPE
Vendor Product Version / Range
andreahaku llm_memory_mcp to f11dc8bcff3ff8cf943a2945f99ff3b0bdc8a6d0 (inc)

Helpful Resources

Exploitability

CWE
CWE Icon
KEV
KEV Icon
CWE ID Description
CWE-77 The product constructs all or part of a command using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify the intended command when it is sent to a downstream component.
CWE-74 The product constructs all or part of a command, data structure, or record using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify how it is parsed or interpreted when it is sent to a downstream component.

Attack-Flow Graph

AI Quick Actions

Instant insights powered by AI
Executive Summary

This is a command injection vulnerability in the andreahaku llm_memory_mcp project. The auto.capture function in src/autolearn/GitHooksManager.ts improperly handles a user-controlled 'hash' argument. When this hash is passed to a shell command via execSync without validation or escaping, an attacker can inject arbitrary OS commands. The attack requires local execution and affects the auto-learning system that processes Git commits tagged with #kb.

Detection Guidance

Check for the presence of the llm_memory_mcp project in your system. Inspect the files src/autolearn/GitHooksManager.ts and src/index.ts for the auto.capture function. Look for execSync calls that use user-controlled commit hash parameters without validation.

Impact Analysis

If you run the llm_memory_mcp server with auto-learning enabled, an attacker with local access could execute arbitrary commands on your system with the same privileges as the server process. This could allow them to read or modify files, install malware, or escalate privileges. The vulnerability specifically targets the Git commit hash parameter used in auto-learning.

Compliance Impact

This vulnerability could lead to unauthorized code execution on systems handling sensitive data, potentially violating GDPR's integrity principle or HIPAA's security requirements for protected health information. A successful exploit might allow attackers to access, modify, or exfiltrate regulated data, resulting in compliance breaches and legal consequences.

Mitigation Strategies

Stop using the auto.capture feature immediately. Validate all commit hash inputs against a strict Git revision pattern. Replace execSync with a safe subprocess API that passes revision values as separate arguments. Ensure no auto-learning is initialized for Git repositories until patched.

Chat Assistant

Ask questions about this CVE
Hi! I’m here to help you understand CVE-2026-19282. Ask me anything about the vulnerability, its impact, or mitigation strategies.
0/70

EPSS Chart