ClawHub
Back to skill

Security audit

Codebase Explorer

Security checks across malware telemetry and agentic risk

Overview

This is a low-risk documentation skill that helps an agent inspect a repository and create onboarding guidance.

Install this only for repositories you are comfortable letting an agent inspect. For private or sensitive projects, ask the agent to avoid secrets and review any generated CLAUDE.md or onboarding guide before sharing it.

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 (2)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The trigger phrases include very broad natural-language requests such as 'understand this codebase', 'analyze this repo', and 'walk me through', which are common user utterances and can cause the skill to activate when the user did not explicitly intend to invoke it. This increases the chance of unintended context capture or execution of a repo-wide analysis workflow, especially in multi-skill environments where activation should be precise.

Vague Triggers

Medium
Confidence
82% confidence
Finding
The 'When to Use' section uses broad activation guidance like 'First time opening a project' and 'help me understand this codebase,' which lacks strict boundaries and can encourage opportunistic activation beyond the user's precise request. In practice, that can make the skill over-trigger and perform expansive repository reconnaissance when a narrower answer was intended.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.