ClawHub
Back to skill

Security audit

business-ai-expert

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed advisory skill for business AI strategy and does not install code, access data, or request elevated authority.

Installers should understand that this skill will bias responses toward structured business AI consulting and may include China-market platforms and compliance concepts by default. For other regions or narrow technical questions, users should specify the target market and desired scope.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger condition is broad enough to match a wide range of general business or AI questions, increasing the chance that this skill activates outside its intended scope and overrides a more appropriate, narrower skill. In a strategic advisory skill, overbroad routing can cause misleading recommendations, irrelevant domain assumptions, and unnecessary exposure to the skill’s embedded biases or constraints.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill hard-codes China-specific market assumptions and platform references without requiring the user to indicate a China-market context. If triggered for users in other jurisdictions, it can skew advice toward unsuitable platforms, regulatory frameworks, and channel strategies, producing materially incorrect or noncompliant business guidance.

Content

No source excerpt is available for this finding.