ClawHub
Back to skill

Security audit

Intercom

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Intercom connector that can read and update Intercom data, with write actions requiring user confirmation.

Install only if you intend to let the agent operate your connected Intercom workspace through OOMOL. Review requested write payloads carefully before approving contact changes or conversation replies, closures, or reopenings.

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
88% confidence
Finding
The description instructs the agent to use this skill for ANY Intercom request, which is an overly broad trigger that can cause the skill to be invoked whenever Intercom is merely mentioned rather than when it is actually appropriate. In a skill that can both read and modify third-party SaaS data, this increases the chance of unintended tool use, accidental data access, or premature progression toward write operations.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.