ClawHub
Back to skill

Security audit

Testimonial Collector

Security checks for vulnerabilities and agentic risk

Overview

This is a plain Markdown guide for requesting, editing, and organizing client testimonials, with no code execution or hidden behavior.

Before installing, treat this as marketing workflow guidance. Use it only with clients who have agreed to provide testimonials, confirm approval for edits and attribution, and protect any testimonial spreadsheet or document that contains client-identifiable information.

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 (2)

Vague Triggers

Medium
Confidence
93% confidence
Finding
The description says to use the skill when someone "needs social proof" or "wants to collect feedback," which are broad, common situations rather than narrowly scoped trigger conditions. Because the file does not provide explicit trigger boundaries or negative examples, this could cause unintended invocation in unrelated feedback or marketing contexts.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The skill explicitly recommends storing identifiable testimonial data such as client name, company, quote, permission status, and usage history, but it does not include a clear privacy, retention, or consent safeguard beyond a general approval note earlier in the document. In contexts involving personal data, this can lead to over-collection, unauthorized reuse, or retention of client-identifiable information without adequate notice or controls.

Static analysis

No suspicious patterns detected.