ClawHub
Back to skill

Security audit

HeyReach

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed HeyReach connector helper with limited `oo` CLI access and confirmation guidance for state changes.

Install only if you are comfortable letting your agent use your OOMOL-connected HeyReach account via the `oo` CLI. Review write payloads before approving them, and treat the one-time installer/login/connection steps as setup actions you should run only when needed.

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
91% confidence
Finding
The skill description is overly broad: it directs the agent to use this skill for ANY HeyReach-related request instead of calling the API directly. That creates an over-triggering risk where loosely related prompts may invoke a powerful integration unnecessarily, increasing the chance of unintended data access or user-confusing actions, especially because the skill includes both read and write capabilities.

VirusTotal

60/60 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.