ClawHub
Back to skill

Security audit

Pay

Security checks for vulnerabilities and agentic risk

Overview

This payment-advice skill is a Markdown-only guide that gives payment, card, dispute, and fraud-safety guidance without taking payments or accessing accounts.

Before installing, treat this as general payment guidance rather than personalized financial advice. For disputes, fraud, card rewards, and bill decisions, confirm details with your bank or card issuer, and do not let any agent initiate payments or account changes without your explicit approval.

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
Confidence
94% confidence
Finding
The trigger list is broad and ambiguous enough that the skill may activate for general payment-related queries without clear user intent to use this specific capability. In a payments context, unintended activation is more sensitive because the skill can influence financial decisions, dispute handling, and bill-management advice, increasing the chance of inappropriate or unsafe guidance being surfaced.

Static analysis

No suspicious patterns detected.