ClawHub
Back to skill

Security audit

customer-report-export-desk

Security checks for vulnerabilities and agentic risk

Overview

This markdown-only skill performs narrow, user-requested customer report formatting without hidden execution, persistence, credentials, or private-file access.

Installers should treat this as a simple customer-report formatting helper. Use it only with customer data the user intentionally provides in the current request, and avoid invoking a stage when the request does not clearly ask to prepare a field or assemble an export row.

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
91% confidence
Finding
The top-level instruction to 'Invoke the stage requested by the user' combined with broad 'customer reporting work' language can cause the agent to select and run a stage on loosely related requests without strong gating. That increases the chance of unintended tool invocation, data transformation, or chaining between stages when the user's intent is ambiguous, especially in workflows handling customer records.

Static analysis

No suspicious patterns detected.