Agentic Mcp Server Builder Conflict

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed MCP scaffolding helper that can create starter files, with a broad opt-in path override users should handle carefully.

Run the scaffold script in dry-run mode first and point scaffold_root and --output at a new project directory. Avoid --allow-outside-workspace unless you deliberately want files written outside the current workspace, because non-dry-run mode can overwrite the fixed starter filenames it creates.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
86% confidence
Finding
The skill instructs the agent to run a local scaffold script and read a reference file, which implies file read/write behavior, but the skill does not declare corresponding permissions. This creates a trust and review gap: consumers may believe the skill is metadata-only while it can materially modify the workspace by generating starter artifacts.

Context-Inappropriate Capability

Medium
Confidence
93% confidence
Finding
The `--allow-outside-workspace` flag explicitly disables the workspace-boundary check and permits scaffolding to arbitrary resolved paths on the filesystem. In an agentic context, this broadens a project scaffolding tool into a general file-writing primitive, which can overwrite or plant files outside the intended project scope if untrusted input controls `scaffold_root`.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal