agent-memory-mcp

Pass

Audited by Gen Agent Trust Hub on Aug 7, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to clone a repository from https://github.com/webzler/agentMemory.git. This is a standard developmental procedure and the destination is a public GitHub repository.
  • [COMMAND_EXECUTION]: The skill contains standard development commands such as npm install, npm run compile, and npm run start-server. These are intended for the local setup of the Model Context Protocol (MCP) server as described in the skill's purpose.
  • [DATA_EXFILTRATION]: No evidence of unauthorized data access or transmission to external domains was found. The dashboard runs on localhost:3333.
  • [PROMPT_INJECTION]: No attempts to bypass safety filters or override agent behavior were detected in the instructions.
  • [REMOTE_CODE_EXECUTION]: While the skill installs dependencies via npm, it does not perform automated piped-execution (e.g., curl | bash) or use unverified remote scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 7, 2026, 09:22 PM
Security Audit — agent-trust-hub — agent-memory-mcp