ClawHub
Back to skill

Security audit

DTC Helper

Security checks for vulnerabilities and agentic risk

Overview

This is a marketing-analysis helper for DTC ads, with no code execution, persistence, hidden data movement, or privileged account actions in the artifact.

Use this skill for DTC ecommerce ads analysis, and provide only the minimum business metrics needed. Do not share ad-account credentials or unnecessary customer data; aggregated snapshots are enough for the described workflow.

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
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger keywords are broad, generic marketing and ecommerce terms like 'conversion', 'optimize', and 'campaign', which can cause this skill to activate for many unrelated requests. Over-broad invocation increases the chance the agent applies DTC ads guidance in the wrong context, leading to confusing, irrelevant, or unsafe task routing decisions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.