ClawHub
Back to skill

Security audit

Dispute Letter

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward dispute-letter drafting aid, with privacy caution needed for the financial details users may provide.

Before using it, provide only the minimum details needed to identify the disputed item. Mask full account numbers, avoid SSNs or login credentials, and redact unnecessary statement or ID information from any supporting documents.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill explicitly asks for account/reference numbers, billing details, evidence, and recipient information, but it does not warn users to minimize, redact, or carefully handle sensitive personal and financial data. In this context, users may overshare full account numbers, statements, IDs, or other high-risk documents in prompts or attachments, increasing the chance of privacy exposure, data retention, or downstream misuse.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

The description lists several example uses, but it does not define clear boundaries for when the skill should not activate or provide negative examples. Phrases like 'Use when asked to dispute' are fairly broad in a general assistant context and could overlap with ordinary requests about complaints or billing issues.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.