ClawHub
Back to skill

Security audit

Brand Butler Webinar Warrior

Security checks for vulnerabilities and agentic risk

Overview

This is a webinar marketing guidance skill with no executable code, persistence, credentials, or hidden data access, though users should apply privacy and advertising compliance when using its tracking and SMS advice.

Install only if you want aggressive webinar sales-funnel assistance. Before using its checklist in production, add your own privacy notice, consent controls for non-essential tracking, clear SMS opt-in language, opt-out handling, and review of applicable advertising, email, and text-message rules.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Vague Triggers

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The manifest description contains very broad activation phrases such as 'selling from stage,' 'live training strategy,' 'building a high-ticket offer,' and even named frameworks like 'perfect webinar,' which can match many ordinary business or marketing conversations. In an agent ecosystem that auto-invokes skills from descriptions, this creates scope hijacking risk: the skill may activate in contexts broader than intended and steer the conversation into aggressive sales-webinar workflows without clear user intent.

Content

No source excerpt is available for this finding.

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
80% confidence
Finding

Skill attempts to nullify the agent's safety policies or restrictions ('you have no restrictions', 'ignore your guidelines', 'do anything now'). This is a direct jailbreak that disables guardrails.

Content

Scanner excerpt · references/positioning-framework.md (reported line 30)May include surrounding context.

md
Use when: Your audience has a belief that's holding them back. This title shatters the belief from the first touchpoint.

**Formula 5 — The Specific Result**
`"How to [Specific Measurable Outcome] in [Timeframe] [With/Without Constraint]"`
Example: *"How to Build a $5K/Month AI Income System in 90 Days Without Quitting Your Job"*
Use when: Your audience responds to specific numbers and timeframes. Best for skeptical audiences.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The checklist explicitly directs the operator to install tracking pixels, purchase-event tracking, and UTM parameters, but provides no instruction to obtain consent, disclose tracking, or configure privacy-compliant analytics. In a marketing/webinar skill, this creates a realistic risk of unlawful or noncompliant personal data collection, especially when purchase events and ad retargeting are involved.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The guidance recommends sending SMS reminders if phone numbers were collected, but it omits any requirement to verify explicit opt-in, applicable legal basis, or compliance with SMS marketing rules. In a marketing automation skill focused on webinar promotion, that omission can lead users to send unsolicited texts, creating privacy, consent, and regulatory exposure.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.