ClawHub
Back to skill

Security audit

Enterprise Code Review

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward code-review workflow that reads code or PR diffs when asked and produces a structured review report.

Install is reasonable for code review use. Before using it, give the agent a clear target such as a file set, branch, commit, or PR URL, and avoid providing secrets unless they are intentionally part of the code-review context.

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
90% confidence
Finding
The trigger condition is very broad, activating on generic requests to review code, PRs, or commits without clear scoping or authorization constraints. In practice, this can cause the skill to engage on unintended inputs and fetch or inspect arbitrary repository content, increasing the chance of over-collection, misuse of tooling, or unintended access to sensitive code during agent operation.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.