ClawHub
Back to skill

Security audit

Security Intelligent Cs

Security checks for vulnerabilities and agentic risk

Overview

This is a static banking customer-service guidance skill with compliance safeguards and no executable code or hidden persistence.

Install only in a setting where banking or securities customer-service guidance is intended. Review and narrow the trigger phrases if accidental activation would be a problem, and replace all sample timelines, fees, routing rules, and retention language with your institution's approved policies before production use.

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
Confidence
95% confidence
Finding
The trigger list is broad and includes generic banking terms such as 'FAQ', 'banking service', '查询', and '转账', which can match ordinary conversations unrelated to the specialized skill. In a financial context, unintended activation is more dangerous because it may cause the assistant to enter regulated-service behavior, present procedural guidance, or solicit sensitive workflow inputs when the user did not intend to invoke this skill.

Natural-Language Policy Violations

Medium
Confidence
90% confidence
Finding
Marking Chinese triggers as '优先' establishes a language-routing preference without explicit user choice, which can lead to language mismatches and misclassification of user intent. In a banking and securities support setting, that increases operational and compliance risk because misunderstood requests about funds, complaints, or account actions can produce incorrect guidance or improper handling.

Static analysis

No suspicious patterns detected.