ClawHub
Back to skill

Security audit

Cloudflare Docs

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Cloudflare documentation lookup connector with read-only listed actions and conditional setup guidance.

Before installing, be aware this skill routes Cloudflare Docs lookups through the OOMOL oo CLI and may require an OOMOL login or provider connection. Its listed actions are read-only, but review any live connector schema before running an action and do not proceed with setup if you do not want to use OOMOL for documentation access.

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
94% confidence
Finding
The trigger text says to use this skill for ANY Cloudflare Docs request and instead of calling the API directly, which is an overly broad routing rule. Broad mandatory invocation can cause the agent to select this skill in cases where a narrower, safer, or more appropriate tool should be used, increasing the chance of unnecessary command execution and reducing contextual security checks.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.