ClawHub
Back to skill

Security audit

Pushsafer

Security checks for vulnerabilities and agentic risk

Overview

This Pushsafer skill is a coherent connector wrapper that can list devices/groups and send notifications, with write actions disclosed and requiring user confirmation.

Before installing, be aware that this skill uses your OOMOL-connected Pushsafer account and can send push notifications. Review notification payloads carefully before approving `send_message`, and only run the CLI install or account-connection setup if you trust OOMOL and need the connector configured.

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
93% confidence
Finding
The description says to use this skill for ANY Pushsafer request and instead of calling the API directly, which is an overly broad trigger that can cause the agent to invoke the skill in situations where a narrower or safer path would be more appropriate. Because this skill includes a state-changing `send_message` action, broad routing increases the chance of unintended external side effects, especially if user intent is ambiguous.

Static analysis

No suspicious patterns detected.