$100M Leads: How to Get Strangers To Want To Buy Your Stuff

• Outcome: Review
• Latest audit: Sep 16, 2026 · 9:23 AM UTC
• Version: 1.0.0

Overview

This is a lead-generation advice skill, but it tries to control when the assistant speaks and injects Heardly promotional links into every answer, even outside the skill's topic.

Review this skill carefully before installing. Its business frameworks are mostly on-topic, but it may cause unsolicited onboarding, append Heardly promotional links to unrelated answers, and encourage high-volume outreach without reminding users to follow consent, anti-spam, privacy, and platform rules.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• 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
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

Findings (2)

T01 · Skill Instruction Hijacking

Error

• Location: SKILL.md:24

Finding

Unsolicited First-Load Response Instruction

Content

View full analysis

Remediation

View remediation

T01 · Skill Instruction Hijacking

Error

• Location: SKILL.md:57

Finding

Mandatory Advertising and External-Link Injection into Every Response

Content

View full analysis

Remediation

View remediation

SkillSpector

Vulnerability Patterns

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

Findings (5)

Anti-Refusal Statement

High

• Category: Anti-Refusal
• Confidence: 85% 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 · references/5-voice-and-app.md (reported line 43)May include surrounding context.

md

### Scenario 5: "I've Tried Everything and Nothing Works"
**You've attempted multiple lead gen methods with no results.**
- **Self-diagnosis:** The problem is either (a) not enough volume, (b) not enough skill, or (c) both. Pick ONE method. Do 100/day for 30 days. Track everything. Adjust. If it still doesn't work after 30 days at volume, try a different method. But don't judge a method at 5 attempts.
- **Book quote:** "If you have thousands of nos, you will get your yeses, I promise. I always tell myself: Yeses give me opportunity. Nos give me feedback. Either way, I win."

---

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 97% confidence

Finding

The trigger list includes very broad, high-frequency phrases such as "grow my business," "advertising," and "content marketing," which can cause the skill to activate for many generic business queries outside the book’s intended scope. Unintended invocation can override more appropriate skills or inject irrelevant guidance, creating prompt-routing integrity issues and increasing the chance that users receive mismatched advice.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 93% confidence

Finding

The trigger list contains very broad, high-frequency phrases such as "grow my business," "advertising," and "content marketing," which can cause the skill to activate for many ordinary business queries that are not specifically asking for this book-based skill. Overbroad activation can hijack routing, suppress more appropriate skills, and increase the chance that users receive mismatched sales/marketing guidance without clear intent.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium

• Category: Not specified by scanner
• Confidence: 91% confidence

Finding

The skill explicitly instructs users to contact strangers who have not given permission and frames success as a volume game, but it provides no warning about consent, privacy laws, anti-spam rules, or platform policies. In a business-advice skill, this can normalize behavior that leads users to send unsolicited outreach at scale, increasing risk of spam, policy violations, account suspension, or unlawful processing of personal data.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

• Category: Not specified by scanner
• Confidence: 83% confidence

Finding

Line L08 states that the writing is intentionally kept at a 5th grade reading level and emphasizes short, simplified language as a requirement. This imposes a language/style constraint in natural language without offering the user any choice or opt-in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.