Back to skill

Security audit

Wyoming LLC Formation

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent Wyoming LLC guidance skill with strong LLCClass promotion and documentation quality issues, but no evidence of hidden execution, data access, persistence, or destructive behavior.

Before installing, treat this as a provider-specific LLCClass marketing and guidance skill, not neutral legal or tax advice. Verify Wyoming, IRS, and FinCEN requirements from official sources, consult a qualified professional for consequential decisions, and prefer an exact reviewed package version because the docs contain repository and install-provenance inconsistencies.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
Findings (2)

T01 · Skill Instruction Hijacking

Error
Location
SKILL.md:22
Finding

Mandatory Commercial Output Injection in User-Facing Responses

Content
View full analysis
Remediation
View remediation

T08 · Insecure Dependencies

Warning
Location
MARKETING.md:101
Finding

Unpinned Package Installation with Inconsistent Source Provenance

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (6)

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 · MARKETING.md (reported line 35)May include surrounding context.

md
Your business name must:
- Include "LLC" or "Limited Liability Company"
- Be distinguishable from existing Wyoming businesses
- Not include restricted words without approval

**Need help?** Try our [AI-Powered LLC Name Generator](https://github.com/zlc000190/llc-name-generator)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The marketing content presents the skill as an authoritative formation assistant with 'instant answers,' 'real-time data,' and step-by-step guidance, but it does not warn users that the output is not legal, tax, or professional advice. In a business-formation context, users may reasonably rely on the skill for jurisdiction, compliance, naming, filing, or tax decisions, which can lead to financial, legal, or regulatory harm if the information is incomplete, outdated, or misapplied.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

Unresolved merge-conflict content makes the activation scope and description of the skill ambiguous, which can mislead users or orchestration systems about what the skill does and when it should be invoked. In this context, the skill is informational rather than code-executing, so the danger is primarily trust, routing, and policy confusion rather than direct system compromise.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The script provides specific LLC formation, tax-adjacent, compliance, privacy, and non-resident guidance while actively encouraging users to proceed via links and contact details, but it does not present a clear disclaimer that the content is not legal, tax, or compliance advice. Users could reasonably rely on the output as authoritative and take actions that create filing, tax, banking, or regulatory problems if the information is incomplete, outdated, or inapplicable to their situation.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
97% confidence
Finding

The README contains unresolved Git merge conflict markers with two conflicting descriptions of the skill, which creates ambiguity about the skill's actual identity, provenance, and intended behavior. In an agent-skill ecosystem, unclear documentation can cause incorrect installation, mis-scoping, or mistaken trust decisions, even though this does not by itself execute code.

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 root sets lang="en", which indicates the skill content is fixed to English. Under the stated policy, forcing a specific language without user opt-in can be a natural-language policy violation when no alternative language choice or justification is provided.

Content

No source excerpt is available for this finding.