ClawHub
Back to skill

Security audit

Modjo AI

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Modjo AI data-retrieval integration with no hidden code, persistence, or destructive behavior in the artifact.

Install this only if you want Codex to read data from a connected Modjo AI account through OOMOL. Review the Modjo permissions on that connection because call transcripts, contacts, users, and deal data may be sensitive, and avoid using it for prompts that do not actually require Modjo AI data.

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 trigger phrase directs the agent to use this skill for "ANY Modjo AI request," which is broader than a narrowly scoped capability declaration and can cause the skill to be selected for loosely related prompts. In an agentic environment, overbroad routing increases the chance of unintended tool invocation and unnecessary access to connected enterprise data, even though the listed actions are read-only.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.