ClawHub
Back to skill

Security audit

event-driven-coordinator

Security checks across malware telemetry and agentic risk

Overview

The skill appears to be advisory and purpose-aligned, with only a routing-scope concern to keep in mind.

This looks safe to install for its stated advisory use. Review the trigger wording so the skill is invoked only for the intended niche, and avoid relying on it for unrelated planning or specialist decisions without user direction.

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
89% confidence
Finding
The skill description is broad enough that it could be invoked for loosely related requests such as general system design, coordination, or workflow planning, causing the agent to activate outside its intended niche. Overly permissive routing increases the chance of inappropriate delegation, confused-deputy behavior, or unsafe reliance on this skill in contexts where stricter specialist constraints should apply.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.