agent-memory-mcp-v2

Fail

Audited by Gen Agent Trust Hub on Aug 7, 2026

Risk Level: HIGHEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill clones an external repository from a third-party source (https://github.com/webzler/agentMemory.git) that is not affiliated with the author (diegosouzapw) or a trusted organization.- [REMOTE_CODE_EXECUTION]: The workflow requires the agent to download external code and execute it via npm commands (install, compile, start-server), posing a risk of executing unvetted malicious scripts.- [COMMAND_EXECUTION]: The skill instructions include running shell commands to start servers and dashboards on the local machine which interact with the user's workspace.- [DATA_EXFILTRATION]: The skill facilitates passing absolute workspace paths to external scripts and starting a local web dashboard (http://localhost:3333), which could be leveraged to expose or exfiltrate local data.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Aug 7, 2026, 09:22 PM
Security Audit — agent-trust-hub — agent-memory-mcp-v2