ClawHub
Back to skill

Security audit

Automation Recipe Book

Security checks across malware telemetry and agentic risk

Overview

This automation skill is not clearly malicious, but it asks for broad write and command authority for persistent workflow automation without enough scoping or review controls.

Install only if you want an agent to help create and manage persistent automation recipes. Review generated or imported recipes before enabling them, especially anything that runs commands, writes files, posts content, sends notifications, touches business systems, or comes from a community source.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Intent-Code Divergence

Medium
Confidence
88% confidence
Finding
The skill promises that `dry-run` produces no side effects, yet the same document advertises powerful state-changing capabilities such as `write`, `exec`, `import`, `install`, and `rollback` without any concrete isolation or enforcement mechanism. In an agent context, this can mislead users or downstream systems into trusting a supposedly safe mode that may still trigger filesystem or environment changes.

Vague Triggers

High
Confidence
93% confidence
Finding
The activation text is extremely broad, covering generic efficiency, automation, batch processing, and workflow optimization use cases. In agent-routing systems, such broad triggers can cause the skill to activate on many unrelated requests, increasing the chance that high-risk tools like `exec` and `write` are exposed in contexts where the user did not specifically request system modification.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The usage example shows automatic generation and saving of a recipe to the workspace and asks whether to enable it, but it does not clearly warn up front that files will be created or modified on disk. In agent environments, normalizing silent file creation increases the risk of unintended persistence, configuration drift, or unsafe automation being introduced without informed consent.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill documents exporting, importing, and installing recipes from external or community sources without any safety warning, provenance checks, or review requirement. External recipes can embed risky actions, invoke privileged tools, or alter workflows, making this especially dangerous in a skill that already advertises `exec` and `write` capabilities.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.