ClawHub
Back to skill

Security audit

Project Engineering

Security checks across malware telemetry and agentic risk

Overview

The skill is a disclosed software-engineering workflow that uses local project inspection and clearly gates writes or external actions on user authorization.

Before installing, understand that this skill is meant for coding-agent work and may read repository structure, Git status, build manifests, and related project files. Use it on repositories you are comfortable letting the agent inspect, and give separate explicit approval for commits, pushes, deployments, migrations, credential changes, or production operations.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Lp3

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding
The skill instructs the agent to read repository files, inspect Git state, run a local Python inventory script, and potentially modify files when implementing changes, but it does not declare corresponding permissions. This creates a capability/permission mismatch: a host may load the skill under the assumption it is low-privilege while the instructions encourage shell, filesystem, and environment access, increasing the risk of over-broad execution or policy bypass.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.