Lead Gen Pipeline

• Outcome: Review
• Latest audit: Sep 16, 2026 · 4:55 AM UTC
• Version: 1.0.0

Overview

This skill needs Review because it can automatically publish demo websites and send cold pitch emails from a Gmail account using scraped business data without enough review, consent, or sender-identity controls.

Install only if you intend to run a cold-outreach workflow and can review every recipient, sender identity, email body, and demo page before anything is sent or published. Configure your own authorized business identity, use private or noindex previews, escape and validate all scraped data, remove unsupported claims, and keep clear deletion/retention controls for leads and deployed demos.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Insecure Skill Coding Practices: Finds exploitable flaws such as hardcoded secrets or command injection
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally

Findings (3)

T01 · Skill Instruction Hijacking

Error

• Location: SKILL.md:68

Finding

Hardcoded Third-Party Branding in Automated Outbound Emails

Content

View full analysis

Remediation

View remediation

T09 · Insecure Skill Coding Practices

Error

• Location: references/demo-site-template.md:9

Finding

Unescaped Web-Derived Data Inserted into Publicly Deployed HTML

Content

View full analysis

[BUSINESS NAME] | [TRADE] in [CITY]

[BUSINESS NAME]

[PHONE]

[BUSINESS NAME]

Professional [TRADE] Services in [CITY] — Licensed, Insured & Ready to Help

Call Now: [PHONE]

Our Services

[EMOJI1]

[SERVICE 1]

[EMOJI2]

[SERVICE 2]

[EMOJI3]

[SERVICE 3]

[EMOJI4]

[SERVICE 4]

...[truncated 3574 chars]

Remediation

View remediation

other

Warning

• Location: references/demo-site-template.md:58

Finding

Automatic Publication of Unverified Business Claims

Content

View full analysis

Professional [TRADE] Services in [CITY] — Licensed, Insured & Ready to Help

✅ Licensed & InsuredFully certified for your protection

⚡ Fast ResponseSame-day service available

💰 Fair PricingFree estimates, no hidden fees

📍 LocalProudly serving [CITY] & surrounding areas

``` ### Technical Analysis The qualification process collects basic listing and website information, but it does not collect or verify licensing, insurance, certification, response-time guarantees, estimates, or pricing policies. Nevertheless, the template presents all of these as affirmative facts under the selected business's real name and telephone number. The workflow then deploys the page publicly before contacting the business. No requirement exists to obtain authorization from the business, label the page prominently as an unofficial mock-up, restrict access, or prevent search-engine indexin ...[truncated 1533 chars]

Remediation

View remediation

SkillSpector

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (4)

Missing User Warnings

High

• Category: Not specified by scanner
• Confidence: 98% confidence

Finding

The skill explicitly supports automated cold outreach to real businesses and can trigger emailing in full-auto mode without any embedded user warning, confirmation gate, or consent check. That creates a significant risk of unauthorized external contact, spam, reputational harm, and policy violations, especially because the workflow also personalizes and sends messages at scale.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 90% confidence

Finding

The trigger phrase 'run the pipeline' is broad and could match ordinary user requests without making clear that the action includes scraping businesses, generating sites, deploying them, and sending external emails. In this skill's context, that ambiguity is more dangerous because invocation can cascade into multi-step autonomous actions with real-world effects.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium

• Category: Not specified by scanner
• Confidence: 90% confidence

Finding

The skill states that it tracks all leads in leads.md and later instructs deployment of demo sites to a VPS, but it does not clearly warn users that business contact data will be stored and generated content may be publicly reachable. This can lead to unintended retention and publication of third-party business data and demo content, increasing privacy, confidentiality, and operational risk.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

• Category: Not specified by scanner
• Confidence: 95% confidence

Finding

The HTML template sets lang="en", which enforces English as the document language. Under the policy, forcing a specific language or locale without offering user choice can be a natural-language policy violation.

Content

No source excerpt is available for this finding.