Back to skill

Security audit

USA Business Migration Planner

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill benign with high confidence: the completed scan found no executable scripts or AIG findings, while Skillspector flagged broad activation wording that could invoke it for unrelated requests.

Consider the unclear purpose and broad activation wording before installing; these could lead to the skill being invoked when you do not expect it. The scan was complete and the verdict is benign, but benign does not mean risk-free.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (6)

Broad activation keywords can invoke the skill for unrelated requests.

Medium
Category
Trigger Abuse
Confidence
93% confidence
Finding

The usage section lists generic keywords such as create, code, and agent without requiring the specific terminal-editor context. Although the example trigger sentences are more specific, nothing limits keyword matching to that context or excludes unrelated coding and agent requests.

Content

No source excerpt is available for this finding.

Generic activation keywords and open-ended invocation criteria can trigger the skill on unrelated requests.

Medium
Category
Trigger Abuse
Confidence
99% confidence
Finding

The trigger list includes generic terms such as 'create', 'code', 'agent', and 'vibe', which occur in many requests unrelated to the terminal-based code-review and editing requirement. Line 4 reinforces this broad scope by activating on requests for a practical workflow, artifact, checklist, or analysis without clear exclusions.

Content

No source excerpt is available for this finding.

Generic keywords can activate the skill outside its intended terminal code-editing context.

Medium
Category
Trigger Abuse
Confidence
99% confidence
Finding

The trigger list includes broad terms such as create, code, agent, and vibe, and L04 likewise presents generic terms as activation conditions. These terms occur in many unrelated requests, with no explicit requirement that the request concern the described terminal editor workflow and no exclusion conditions.

Content

No source excerpt is available for this finding.

Implicit invocation is enabled without a coherent, specific activation scope.

Medium
Category
Trigger Abuse
Confidence
97% confidence
Finding

The display name suggests US business migration, but the generic, truncated description provides no usable activation criteria, and the default prompt instead describes terminal-based code editing. With implicit invocation enabled, these conflicting signals leave it unclear which requests should activate the skill.

Content

No source excerpt is available for this finding.

Usage keywords include overly broad terms that could trigger unrelated requests.

Low
Category
Trigger Abuse
Confidence
94% confidence
Finding

The usage keywords include create, code, and agent, which commonly appear in requests unrelated to this skill's terminal-based code-review and editing workflow. Although specific trigger sentences follow, the README does not constrain keyword matching to that workflow or provide exclusion conditions.

Content

No source excerpt is available for this finding.

The usage keywords include broad terms such as "create", "code", "agent", and "vibe" without restricting them to the terminal-editor workflow.

Low
Category
Trigger Abuse
Confidence
90% confidence
Finding

These keywords overlap with many unrelated requests and could cause unintended skill activation. Although the trigger sentences below are more specific, the keyword list does not state that matching also requires the terminal-based, VS Code-style editing context.

Content

No source excerpt is available for this finding.