Skool

• Outcome: Pass
• Latest audit: Sep 12, 2026 · 3:26 AM UTC
• Version: 1.0.0

Overview

This skill is a disclosed Skool operations guide that uses local notes and approved integrations, with repeated safeguards for member-impacting actions.

Install only if you want Codex to keep Skool operating notes in ~/skool/ and help with approved Zapier or webhook workflows. For any live member, access, invite, DM, or billing-adjacent change, keep the skill in preview/advisory mode until you explicitly approve the action and payload.

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

SkillSpector

Vulnerability Patterns

• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (4)

Autonomous Decision Making

Medium

• Category: Excessive Agency
• Confidence: 85% confidence

Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 173)May include surrounding context.

md

This skill NEVER:
- treat unsupported automation as normal just because it can be scripted
- bypass confirmation for live member-impacting changes
- claim a feature exists without checking current Skool docs when exact behavior matters
- turn local memory into a shadow CRM full of unnecessary member data

Autonomous Decision Making

Medium

• Category: Excessive Agency
• Confidence: 75% confidence

Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 174)May include surrounding context.

md

This skill NEVER:
- treat unsupported automation as normal just because it can be scripted
- bypass confirmation for live member-impacting changes
- claim a feature exists without checking current Skool docs when exact behavior matters
- turn local memory into a shadow CRM full of unnecessary member data

## Related Skills

Autonomous Decision Making

Medium

• Category: Excessive Agency
• Confidence: 80% confidence

Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · automation-and-integrations.md (reported line 45)May include surrounding context.

md

- No official Skool CLI is documented in the current official help content.
- Do not assume undocumented endpoints are safe enough for production writes.
- Do not automate posting, commenting, or messaging through unsupported bots when the platform or docs say otherwise.
- Do not ask the user to share Skool credentials with teammates, contractors, or external tools.

## What To Capture After a Working Automation

Vague Triggers

Medium

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

Finding

The skill defines activation using broad triggers such as any mention of Skool, classroom, approvals, calendar events, courses, Zapier, or member lifecycle work, and also suggests proactive intervention in access-risk, onboarding, or automation scenarios. In an agent setting, this ambiguity can cause the skill to activate outside the user's intent, increasing the chance of unsolicited guidance or member-affecting actions in a sensitive operational domain.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.