ClawHub
Back to skill

Security audit

find-bugs

Security checks across malware telemetry and agentic risk

Overview

This is a read-only code review skill that inspects local branch changes and reports bugs or security issues without installing code, sending data, or modifying files.

Install this only in repositories where you are comfortable with the agent reading branch diffs and changed files. The skill is designed to report findings only, so review its recommendations before deciding what to change.

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
93% confidence
Finding
The skill description includes broad trigger phrases such as 'review changes', 'find bugs', 'security review', and 'audit code on the current branch', which can match many ordinary developer requests and cause the skill to auto-activate in contexts broader than intended. Because this skill instructs the agent to inspect local branch diffs and repository contents, over-broad routing increases the chance of unintended invocation, unnecessary exposure of sensitive code, and prompt-surface expansion from untrusted repository content.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal