ClawHub
Back to skill

Security audit

Ongage

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Ongage connector wrapper that can read and update Ongage contact data through the oo CLI, with write actions requiring confirmation.

Install this only if you intend to let Codex use your OOMOL-connected Ongage account. Review write payloads carefully before approving contact status changes, updates, or upserts, and only run the oo CLI installer or account connection steps 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 trigger text says to use this skill for "ANY Ongage request," which is broader than a narrowly scoped routing rule and can cause the agent to invoke the skill for vague mentions or low-intent references to Ongage. In a write-capable integration, over-invocation increases the chance of unnecessary schema inspection, connector calls, or accidental state-changing workflows being entered when a simpler response or clarification was warranted.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.