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.
Published: 2026-08-08
Score: 4.8 Medium
EPSS: n/a
KEV: No
Impact: n/a
Action: n/a
AI Analysis

Impact

The weakness resides in the auto.capture function within GitHooksManager.ts and allows an attacker to inject arbitrary shell commands by manipulating the hash argument. Because the function executes the hash value directly, an unauthenticated local user who can supply that argument can cause the system to run any command with the privileges of the process. This can lead to the disclosure of sensitive data, modification of system files, or further privilege escalation. The vulnerability is classified as command injection (CWE‑74) and input misvalidation (CWE‑77).

Affected Systems

The affected product is llm_memory_mcp developed by Andreahaku. All releases up to commit f11dc8bcff3ff8cf943a2945f99ff3b0bdc8a6d0 are vulnerable. No versioning schema is used, so the exact impacted versions cannot be enumerated beyond that commit. Users of any tagged version in the repository are potentially affected until a patch is released.

Risk and Exploitability

The CVSS score of 4.8 indicates a moderate risk, but because the exploitation is restricted to local execution, the EPSS score is not available and the vulnerability is not listed in the CISA KEV catalog. An attacker must already have local access to the system or the ability to supply the hash argument to invoke the auto.capture function. In the absence of a known fix, the likelihood of exploitation remains low, but local attackers could still commandeer the process. Administrators should treat this as a local command execution risk requiring monitoring and remediation as soon as an update becomes available.

Generated by OpenCVE AI on August 8, 2026 at 13:20 UTC.

Remediation

No vendor fix or workaround currently provided.

OpenCVE Recommended Actions

  • Watch the project's GitHub repository for a patch or mitigation update.
  • Restrict local user permissions so that only trusted users can invoke the auto.capture function.
  • Implement input validation or sanitization for the hash argument to prevent shell interpretation.
  • If feasible, disable or remove the auto.capture feature until a fix is provided.

Generated by OpenCVE AI on August 8, 2026 at 13:20 UTC.

Tracking

Sign in to view the affected projects.

Advisories

No advisories yet.

History

Sat, 08 Aug 2026 12:30:00 +0000

Type Values Removed Values Added
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.
Title andreahaku llm_memory_mcp GitHooksManager.ts auto.capture command injection
First Time appeared Andreahaku
Andreahaku llm Memory Mcp
Weaknesses CWE-74
CWE-77
CPEs cpe:2.3:a:andreahaku:llm_memory_mcp:*:*:*:*:*:*:*:*
Vendors & Products Andreahaku
Andreahaku llm Memory Mcp
References
Metrics cvssV2_0

{'score': 4.3, 'vector': 'AV:L/AC:L/Au:S/C:P/I:P/A:P/E:POC/RL:ND/RC:UR'}

cvssV3_0

{'score': 5.3, 'vector': 'CVSS:3.0/AV:L/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:L/E:P/RL:X/RC:R'}

cvssV3_1

{'score': 5.3, 'vector': 'CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:L/E:P/RL:X/RC:R'}

cvssV4_0

{'score': 4.8, 'vector': 'CVSS:4.0/AV:L/AC:L/AT:N/PR:L/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:P'}


Subscriptions

Andreahaku Llm Memory Mcp
cve-icon MITRE

Status: PUBLISHED

Assigner: VulDB

Published:

Updated: 2026-08-08T12:15:08.189Z

Reserved: 2026-08-07T15:34:26.745Z

Link: CVE-2026-19282

cve-icon Vulnrichment

No data.

cve-icon NVD

No data.

cve-icon Redhat

No data.

cve-icon OpenCVE Enrichment

Updated: 2026-08-08T13:30:16Z

Weaknesses
  • CWE-74

    Improper Neutralization of Special Elements in Output Used by a Downstream Component ('Injection')

  • CWE-77

    Improper Neutralization of Special Elements used in a Command ('Command Injection')