Back to skill

Security audit

Funnel Builder

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent funnel builder, but it should be reviewed carefully because it enables automated customer-facing sales activity, Telegram use, and trading-related marketing without enough clear user-control and disclosure safeguards.

Install only if you are comfortable with an agent helping create and potentially operate customer-facing sales funnels. Before using Telegram, payment pages, trading-signal pages, public posting, or subscriber messaging, require manual approval, add privacy notices, avoid sending sensitive lead/customer data unnecessarily, and add clear financial-risk disclaimers for any trading-related offer.

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
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (11)

Hidden Instructions

High
Category
Prompt Injection
Confidence
70% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · landing_page.md (reported line 13)May include surrounding context.

GLOBAL STYLE — Apply to all pages

html
<!-- Paste this in the <head> of every landing page -->
<style>
  * { box-sizing: border-box; margin: 0; padding: 0; }
  body {

Hidden Instructions

High
Category
Prompt Injection
Confidence
70% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · landing_page.md (reported line 54)May include surrounding context.

md
[EYEBROW — ex: "Trusted by 200+ founders" or leave empty]
    </p>

    <!-- HEADLINE — the single most important line on the page -->
    <!-- Formula: [Result] for [ICP] without [Pain] -->
    <h1 style="font-size:clamp(2rem,5vw,3.2rem); font-weight:800;
                line-height:1.15; margin-bottom:24px;">

Hidden Instructions

High
Category
Prompt Injection
Confidence
70% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · landing_page.md (reported line 156)May include surrounding context.

md
</li>
    </ul>

    <!-- AGITATION — what it costs to stay in this situation -->
    <div style="background:#1a0000; border:1px solid #3a0000; border-radius:8px;
                padding:24px; margin-top:40px;">
      <p style="color:#fca5a5;">

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill explicitly enables outbound requests to public sites and the Telegram Bot API, and it requires TELEGRAM_BOT_TOKEN and TELEGRAM_CHAT_ID, but it does not clearly warn users what business data, lead data, or workspace-derived content may be transmitted off-platform. In a funnel-building skill, collected ICP details, offer data, and lead information are likely to be sensitive commercial or personal data, so silent external transmission creates a real privacy and data-governance risk.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trading-related landing page templates emphasize profits, signals, and proof of returns but omit any prominent disclaimer that performance is not guaranteed and that users can lose money. In the context of a funnel-building skill that generates persuasive marketing pages, this increases the risk of misleading financial promotion and could expose users to financial harm and regulatory issues.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The file instructs users on "Auto-entrepreneur / Micro-entreprise" registration, a French registration portal, and French VAT thresholds, which are locale-specific operational instructions. The document does not clearly state that this framework applies only to users operating in France or offer a locale selection, creating a natural-language locale policy issue.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

This file includes core workflow steps in French such as 'CHOISIR SA NICHE', 'CRÉER SON OFFRE', and 'BOOKER DES APPELS' while the rest of the skill is in English. That creates a language-policy issue because the skill implicitly forces part of the interaction/documentation into a specific language without user opt-in or justification.

Content

No source excerpt is available for this finding.

Scope Creep

Low
Category
Excessive Agency
Confidence
70% confidence
Finding

Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Content

Scanner excerpt · SKILL.md (reported line 329)May include surrounding context.

md
→ Automate via Make / N8N (no manual intervention after setup)

CLOSE → Sell the system to the creator
  → Package as "I handle everything, you take % of revenue"
  → Or: "Here's the system, implement it" (consulting model)

SCALE → Systematize what works

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

This markdown file explicitly instructs the agent to fill placeholders and save the result to /workspace/funnel/active_funnels/[slug]/email_sequence.md. Because markdown files should warn about behaviors that affect user data or system state, this file-writing behavior should be disclosed more clearly to the user.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

This markdown file contains instructional content that switches into French terms such as "CHOISIR SA NICHE" and "CRÉER SON OFFRE" while the rest of the document is in English. Because the file does not state that the skill is intentionally French-region-specific or provide an opt-in language choice, it may violate language/locale policy expectations.

Content

No source excerpt is available for this finding.

Scope Creep

Low
Category
Excessive Agency
Confidence
70% confidence
Finding

Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Content

Scanner excerpt · masters_frameworks.md (reported line 286)May include surrounding context.

md
CLOSE (structure the deal)
  Revenue share: 20-40% of all sales you generate
  → Creator records content, you build and manage everything
  → Zero upfront cost for creator = easy yes
  → Align incentives: you only earn if they earn

Static analysis

No suspicious patterns detected.