ClawHub

GitHub Cred

Security checks across malware telemetry and agentic risk

Overview

This is a text-only GitHub profile scoring guide with no executable code, credential use, persistence, or hidden behavior.

Install from the ClawHub package when possible. If using the README's manual git clone command, inspect that GitHub repository separately because it may contain files not included in this reviewed text-only bundle.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The invocation examples are broad natural-language phrases such as 'analyze <username>'s github', which can match ordinary conversation rather than a tightly scoped command. In an agent environment, this increases the chance of unintended skill activation, causing the bot to fetch and analyze GitHub data when the user did not explicitly intend to invoke this skill.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal