ClawHub
Back to skill

Security audit

IFTTT

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently connects OpenClaw to IFTTT and includes user-confirmation guardrails for real-world actions, though users should notice that IFTTT automations can affect connected services.

Install this only if you intend to use IFTTT with OpenClaw. Review any OAuth and service-connection prompts carefully, and confirm that proposed Applets, removals, or one-off actions match what you want because they can send messages, change devices, or update connected services.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill description says to use it when the user asks what they can automate or describes an automation like 'when X happens, do Y,' which is broad enough to match many generic requests. That can cause unintended invocation of a high-impact integration skill that can create Applets or run actions against external services, increasing the chance of unnecessary OAuth prompts, over-collection of context, or accidental side-effectful operations if later steps are not carefully confirmed.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The 'When to use' section includes the ambiguous condition 'The user describes an automation: when X happens, do Y,' which may over-trigger this skill for routine natural-language requests unrelated to IFTTT. In this context, overbroad routing is more dangerous because the skill exposes capabilities with real-world side effects, including creating enabled Applets immediately and running one-off actions against connected services.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.