ClawHub
Back to skill

Security audit

RedHat Debugger

Security checks across malware telemetry and agentic risk

Overview

This is a simple debugging workflow skill with no executable code or hidden behavior, though its activation metadata is malformed and should be fixed.

Safe to install for a generic debugging workflow. Before using it, redact secrets from logs and environment details, review any proposed fixes before applying them, and prefer an updated version with explicit trigger phrases instead of the current malformed trigger metadata.

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
97% confidence
Finding
This manifest file includes a `triggers` section, but its value is the non-descriptive `System.Object[]` rather than an explicit list of trigger phrases or activation conditions. That makes it unclear what user input activates the skill and provides no scope, constraints, or negative examples to prevent unintended invocation.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal