ClawHub
Back to skill

Security audit

Rootly

Security checks across malware telemetry and agentic risk

Overview

This appears to be a Rootly-focused skill with one scope-quality concern, but no evidence of malware, deception, exfiltration, destructive behavior, or hidden persistence.

Install only if you intend to use the agent with Rootly. Treat Rootly incident and account data as sensitive, and prefer explicit prompts such as asking the agent to search or update Rootly rather than casual mentions that could load the skill unnecessarily.

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
88% confidence
Finding
The description instructs the agent to use this skill for ANY Rootly request and whenever a task involves Rootly, which is an overly broad routing rule. This can cause unintended invocation on casual mentions of Rootly or on tasks better handled by other tools, increasing the chance of unnecessary data access or inappropriate connector use without clear user intent.

VirusTotal

55/55 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.