ClawHub
Back to skill

Security audit

Dropcontact

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent Dropcontact connector skill that uses OOMOL's `oo` CLI and clearly flags its only state-changing action for user confirmation.

Before installing, understand that submitting enrichment sends contact data to Dropcontact through OOMOL and may consume service credits. Confirm the payload before any `submit_enrichment` action, and only run the first-time CLI install or login steps when you intentionally want to connect your OOMOL account.

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
95% confidence
Finding
The skill description says to use this skill for ANY Dropcontact request, including reading, creating, and updating data, which creates an overly broad trigger scope. This can cause the agent to route all Dropcontact-related tasks through a capability that includes write actions, increasing the chance of unintended state-changing operations when a narrower read-only or task-specific skill would be safer.

Static analysis

No suspicious patterns detected.