ClawHub
Back to skill

Security audit

Work over SSH

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed SSH workflow for working on a user-specified remote Git project, with guardrails around credentials, patches, and high-impact actions.

Install only if you intend agents to work through your configured SSH access. Provide trusted SSH aliases and project paths, do not paste secrets, and review any requested package installs, deployments, service restarts, database mutations, or destructive Git actions separately.

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
95% confidence
Finding
The skill clearly instructs the agent to read remote files and execute shell commands over SSH, yet it declares no explicit permissions. This creates a policy/visibility gap: a caller or enforcement layer may underestimate the skill's capabilities, leading to unintended remote command execution or data access if the skill is invoked in a broader workflow.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.