ClawHub
Back to skill

Security audit

ContactOut

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent ContactOut connector skill that uses the OOMOL `oo` CLI for disclosed people and company lookup actions, with no evidence of hidden, destructive, or deceptive behavior.

Install this only if you intend to use ContactOut through OOMOL and are comfortable with queries that may retrieve personal emails, phone availability, LinkedIn profile data, company enrichment, and account usage stats. Make sure requests are user-directed, review search or enrichment inputs before running them, and watch account billing or credits because actions use the connected ContactOut service.

SkillSpector

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 description says to use this skill for "ANY ContactOut request" and "whenever a task involves ContactOut," which is an overly broad trigger that can cause the agent to invoke the skill in contexts where it is not necessary or where safer, narrower handling would be preferable. Because this skill enables access to sensitive people-search and contact-enrichment functions, broad auto-routing increases the chance of unnecessary exposure of personal data, unintended external queries, and overuse of connected credentials.

Static analysis

No suspicious patterns detected.