ClawHub
Back to skill

Security audit

Meta

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Meta read connector using OOMOL's CLI, with no evidence of hidden mutation, exfiltration, or destructive behavior.

Install this if you are comfortable using OOMOL as the intermediary for your connected Meta business account. Review the live connector schema before actions, and require explicit approval before any future write or destructive Meta operation.

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
92% confidence
Finding
The skill description says to use this skill for ANY Meta request, which creates an overly broad routing trigger with no clear task or permission boundaries. That can cause unrelated or higher-risk Meta operations to be funneled through this connector automatically, increasing the chance of unintended data access or execution in contexts where a narrower skill or direct review would be safer.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.