ClawHub

Beta Code Review

Security checks across malware telemetry and agentic risk

Overview

This is a checklist-style code review skill whose install steps and runtime instructions match its stated purpose.

Install only from a source you trust, especially when using npx or copying into global skill folders. The reviewed package itself appears to be a normal code-review checklist skill with no hidden execution or sensitive access requests.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Rogue AgentSelf-Modification, Session Persistence
  • 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)

Session Persistence

Medium
Category
Rogue Agent
Content
From your project root:

```bash
mkdir -p .cursor/skills
cp -r ~/.ai-skills/skills/testing/code-review .cursor/skills/code-review
```
Confidence
60% confidence
Finding
mkdir -p .cursor/skills cp -r ~/.ai-skills/skills/testing/code-review .cursor/skills/code-review ``` #### Cursor (global) ```bash mkdir -p ~/.cursor/skills cp -r ~/.ai-skills/skills/testing/code-rev

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal