ClawHub
Back to skill

Security audit

AB Test Setup

Security checks for vulnerabilities and agentic risk

Overview

This is a simple A/B test planning skill with no code or data access, though a few trigger words are broad.

Install this if you want help drafting A/B test plans. Be aware that generic words like "experiment" or "variant" may cause the skill to activate in some unrelated discussions, but the inspected artifact does not run code, access data, or change anything on its own.

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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger list includes several generic terms such as "experiment," "variant," and "hypothesis"-adjacent A/B testing language that can appear in ordinary conversations outside the intended domain. This can cause accidental invocation of the skill, leading to irrelevant planning output or unintended interception of user requests, though the skill itself is non-privileged and does not perform sensitive actions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.