ClawHub
Back to skill

Security audit

Appliance Repair Marketing Kit

Security checks for vulnerabilities and agentic risk

Overview

This is a marketing prompt kit with one caution around lawful cold outreach, but it does not contain code, hidden execution, credential access, or persistence.

Review any generated ads, review requests, and outreach before publishing. Use only accurate authorization, EPA, warranty, pricing, and review claims, and source outreach contacts lawfully with opt-outs and applicable anti-spam and platform-rule compliance.

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
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • 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
Findings (2)

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
80% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · README.md (reported line 26)May include surrounding context.

md
## Quick Start (5 minutes)

1. Open `prompts/prompt1-emergency-ads.md`
2. Copy the prompt into Claude
3. Fill in your `[BRACKET]` fields
4. Paste the output into Google Ads

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The marketing plan explicitly promotes 'Direct outreach — email appliance repair shops via Google Maps scrape,' but provides no constraints around consent, applicable anti-spam rules, terms-of-service limitations, or safeguards on collection and use of scraped contact data. In a skill that may operationalize outreach workflows, this can enable bulk unsolicited emailing and questionable scraping practices, creating legal, compliance, and abuse risk.

Content

No source excerpt is available for this finding.