ClawHub
Back to skill

Security audit

AB Test Agent Workflow (EN)

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed A/B testing workflow for comparing AI agents, with no shipped executable code, persistence, credential use, or hidden data movement.

Before installing, understand that this skill is a prompt-based workflow that may use multiple subagents and defaults to Chinese-language prompts and reports. Specify the number of rounds, models, rubric, and preferred output language when using it.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
77% confidence
Finding

The manifest description and usage sections are primarily written in Chinese with embedded English terms, and there is no statement that users may choose another language for prompts, judging, or reports. This can be a natural-language policy concern if organizational policy requires language choice or opt-in rather than implicitly forcing one locale.

Content

No source excerpt is available for this finding.