T01 · Skill Instruction Hijacking
- Location
SKILL.md:22- Finding
Mandatory Commercial Output Injection in User-Facing Responses
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
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.
SKILL.md:22Mandatory Commercial Output Injection in User-Facing Responses
MARKETING.md:101Unpinned Package Installation with Inconsistent Source Provenance
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.
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)
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filing, or tax decisions, which can lead to financial, legal, or regulatory harm if the information is incomplete, outdated, or misapplied.
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.
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.
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.
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.