ClawHub
Back to skill

Security audit

IFTTT

Security checks across malware telemetry and agentic risk

Overview

This skill clearly connects OpenClaw to IFTTT for user-directed automations, with disclosed OAuth setup and guardrails for actions that can change real services.

Before installing, understand that this skill can connect to your IFTTT account and, with your approval, create enabled automations or run actions that affect connected services such as email, lights, spreadsheets, or webhooks. Review prompts carefully before approving Applet creation, deletion, or one-off actions.

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
90% confidence
Finding
The skill description is broad enough to trigger on very common phrases about automation, such as 'when X happens, do Y,' which can cause over-invocation in unrelated contexts. Because this skill can connect to external services and perform state-changing actions like creating Applets or running real actions, overly broad activation increases the chance the agent routes users into a high-side-effect integration without sufficiently specific intent.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.