ClawHub
Back to skill

Security audit

A/B Test Architect

Security checks for vulnerabilities and agentic risk

Overview

This skill is a marketing experiment planning guide with no executable code or hidden system access, though its activation wording is a bit broad.

Installers should expect this skill to help plan conversion experiments and ask for business metrics such as traffic and conversion rates. Be aware it may activate on some generic requests about testing or hypotheses, but it does not appear to run commands, access files, or change systems.

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 activation section uses broad phrases such as "I want to test..." and "write a hypothesis," which can match many ordinary requests that are not specifically asking for this skill. Over-broad routing can cause the agent to invoke this skill in unintended contexts, leading to inappropriate responses, interference with more relevant skills, or accidental collection of extra user context.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.