ClawHub
Back to skill

Security audit

Ba Workbench 1.1.0

Security checks across malware telemetry and agentic risk

Overview

This is a business-analysis reference and template skill with broad trigger language, but no hidden execution, credential use, persistence, or data exfiltration behavior was found.

Install only if you want a broad Chinese-language business-analysis assistant that may activate on common BA terms and append the author's legal/disclaimer/contact text to responses. Review outputs before using them for business decisions, especially financial, compliance, or market claims.

SkillSpector

By NVIDIA
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 (3)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The README advertises very broad natural-language trigger phrases such as '做竞品分析' or '帮我做一份行业分析报告', which are common requests in ordinary conversation. In agent platforms that auto-route or auto-activate skills based on trigger text, this can cause unintended invocation, over-collection of user context, or execution of the wrong specialized workflow without clear user intent.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The trigger list contains broad terms such as 'BA', '市场分析', and '商业分析' that can appear in many unrelated conversations, making unintended invocation likely. This can cause the skill to override normal assistant behavior, inject large amounts of prescriptive content, and append mandatory legal/contact boilerplate in contexts where the user did not request this skill.

Vague Triggers

Medium
Confidence
91% confidence
Finding
The instruction '直接告诉我你要做什么商业分析，BA Skill自动匹配阶段、方法论、框架、工具链' implies automatic activation and broad autonomous scope selection without clear boundaries. This increases the chance the skill will engage on loosely related requests and steer outputs in ways the user did not explicitly ask for.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.