Back to skill

Security audit

Agentmemory Mcp Tools

Security checks across malware telemetry and agentic risk

Overview

This skill is a plain documentation index for agentmemory MCP tools and does not include executable code or hidden behavior.

Install only if you intend the agent to use an agentmemory MCP server. Memory tools may store or retrieve user/workspace context, so review what your MCP server exposes and use audit or delete controls for sensitive entries.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

VirusTotal

56/56 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.