Track vulnerabilities like this one. Sign up free to get alerted when software you use is affected.
6.9

CVE-2026-19282: andreahaku llm_memory_mcp can run unwanted commands via Git hook

CVE-2026-19282 · published 2 months ago
Summary

The llm_memory_mcp component’s GitHooksManager can be tricked into executing system commands when a specially crafted hash is supplied to its auto.capture function. This risk is limited to someone who can run code on the same machine, but it could allow them to run arbitrary commands. Apply any available patches, limit who can invoke the Git hook, and consider disabling or reviewing this feature until it is fixed.

What to do

The CVE record does not list a fixed version. Check the vendor's site or the advisory links below - a fix may already be released.

Affected software
VendorProductAffected versions
andreahaku llm_memory_mcp f11dc8bcff3ff8cf943a2945f99ff3b0bdc8a6d0
Original advisory text
andreahaku llm_memory_mcp GitHooksManager.ts auto.capture command injection
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.
Fix within
Internet-facing 60 days
Internal At next upgrade
  • Not known to be exploited
  • Needs hands-on effort to exploit
  • Gives an attacker partial control
Severity
6.9 Medium
Exploitation
1% chance of attack within 30 days
Type
CWE-77Command Injection
CWE-74Injection
Timeline
Published8 Aug 2026
Updated4 Nov 2026
First seen8 Aug 2026
Sources
CVE-2026-19282 · MITRE
Track software like this
Free during beta