ClawHub
Back to skill

Security audit

Course Creator Coach

Security checks for vulnerabilities and agentic risk

Overview

This is a plain coaching skill for online-course creators, with no executable code or hidden system access.

Safe to install as a course-creation coaching reference. Users should still verify legal, advertising, platform-pricing, and earnings-claim advice against current rules before acting on it.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
80% confidence
Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · SKILL.md (reported line 259)May include surrounding context.

md
- "Build it and they will come" — record first, validate never.
- Fake "first 10 students" countdown timers that reset every page load.
- Misleading "I made $XXX in YY days" income claims without disclaimers (FTC violation).
- Bonus-stack inflation ($50K total value!! Today $497!!!) where bonuses are AI-generated junk.
- Buying email lists or bot-driven webinar attendance.
- Plagiarizing curriculum from another creator's course (copyright + reputation risk).

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill metadata and frontmatter include a very broad trigger list with generic phrases such as "online course," "build a course," and "course creator." In agent-routing systems, overly broad triggers can cause unintended invocation on loosely related user requests, increasing the chance of irrelevant guidance, policy-bypassing context switches, or accidental handling of conversations outside the intended scope.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.