Back to skill

Security audit

Hormozi Squad

Security checks for vulnerabilities and agentic risk

Overview

This is a small business-advice skill with no executable code, network behavior, credential access, or hidden persistence.

Installers should understand this as a Portuguese-forward business coaching skill. Review the broad activation examples if ambiguous routing matters in your OpenClaw setup, but the inspected artifact does not show hidden execution, data access, or persistence.

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
  • Rogue AgentSelf-Modification, Session Persistence
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · SKILL.md (reported line 49)May include surrounding context.

md
## Tasks Disponíveis

- create-offer - Create Grand Slam Offer
- generate-leads - Lead generation strategies
- set-pricing - Value-based pricing
- close-sale - Sales closing framework

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The example invocation phrases are broad business-language requests that could unintentionally trigger this skill during ordinary conversation, causing ambiguous routing or execution without clear user opt-in. In a multi-agent environment, this increases the chance of the agent activating sales/growth workflows when the user only intended to ask a general question.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

The file mixes Portuguese and English throughout the user-facing description and usage guidance, but it does not state whether the skill will respond in one language, preserve the user's language, or allow language selection. That can create an implicit language-policy issue if the skill defaults users into a language without opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The manifest description is written entirely in Portuguese, which can indicate a language-specific skill presentation without offering a user language choice. Under the policy rule, language constraints should either be optional for users or clearly documented as region-specific and justified.

Content

No source excerpt is available for this finding.