ClawHub
Back to skill

Security audit

Coaching Consulting Launch Kit

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown prompt pack for coaching business materials, with a privacy caution around client testimonials but no hidden execution or system access.

Before using this skill with real client stories, get documented permission for names, employers, quotes, salary/revenue figures, and any identifiable circumstances. Use aliases, composites, or aggregated results by default, and label reconstructed or hypothetical material clearly.

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
Category
Not specified by scanner
Confidence
94% confidence
Finding

The prompt explicitly encourages use of real client results, detailed career/salary outcomes, and testimonial quotes, but does not require obtaining informed client consent before collecting, drafting, or publishing identifiable proof assets. In a coaching/consulting context, this can expose sensitive employment, compensation, and personal transformation details, creating privacy, confidentiality, and reputational risk if a user follows the prompt as written.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.