ClawHub
Back to skill

Security audit

AfrexAI Testimonial Collector

Security checks for vulnerabilities and agentic risk

Overview

This is a simple testimonial-writing skill with a privacy/consent caveat but no hidden execution, persistence, or privileged access.

Before publishing generated testimonials, confirm documented customer permission for the quote, attribution, company name, logo, and any results claims; anonymize details where permission is unclear.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill explicitly promotes using real names, titles, companies, and testimonial content as stronger social proof, but provides no guardrails around obtaining consent, honoring privacy preferences, or verifying publication rights. In a marketing workflow, this can lead users to collect or publish personally identifiable information and endorsements without permission, creating privacy, consent, and reputational risk.

Static analysis

No suspicious patterns detected.