ClawHub
Back to skill

Security audit

Beauty Wellness Salon Marketing

Security checks for vulnerabilities and agentic risk

Overview

This is a standalone marketing-template skill for beauty and wellness businesses, with no code execution, persistence, or hidden system access.

Review generated medical-aesthetic claims, testimonials, before/after captions, SMS, email, and referral campaigns with appropriate legal/compliance judgment before publishing or sending. Use only consented contact lists, honor opt-outs, and add treatment-specific safety language where applicable.

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 (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The file contains extensive promotional copy for medical spa services such as laser hair removal, microneedling, and Hydrafacial, but omits user-facing cautions about contraindications, side effects, recovery expectations, and the need for professional suitability assessment. In a health-adjacent context, this can mislead users into treating elective medical/cosmetic procedures as risk-free consumer services, increasing the chance of inappropriate self-selection or deceptive advertising output.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The file describes its purpose in broad natural language as generating service page copy and social proof materials, but it does not define any explicit trigger phrases, scope limits, or negative examples for when this prompt should or should not be used. In a markdown skill context, this ambiguity can cause unintended invocation for generic copywriting requests related to beauty businesses.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The prompt operationalizes retention emails, SMS review requests, referral outreach, and win-back campaigns using client contact data, but it does not instruct the agent or user to verify consent, lawful basis, review-platform policy compliance, data minimization, or broader privacy requirements. The isolated TCPA-style STOP language on SMS is not sufficient because the workflow still encourages outreach and review solicitation that could violate privacy, anti-spam, or platform rules if used with non-consenting clients or in regulated jurisdictions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.