ClawHub
Back to skill

Security audit

Solopreneur

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local solopreneur dashboard helper with incomplete advertised features but no evidence of hidden network access, credential use, persistence, or destructive behavior.

Before installing, be aware that the skill is intended to handle local client, revenue, invoice, pipeline, and priority data under the OpenClaw workspace memory path. The packaged version appears incomplete: only the dashboard script is present, so advertised invoice, pipeline, payment, priority, and review workflows may not work unless added separately.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding
The declared description presents a broader business-management skill with multiple active capabilities: dashboarding, pipeline tracking, invoice drafting, prioritization, and weekly reviews. The supplied code chunk implements only the dashboard display portion. It reads local data and prints summary metrics, which is consistent with the 'private and local' claim, and it does not exhibit undeclared external access or suspicious behavior. However, relative to the declared purpose, the actual behavior is materially narrower, with several advertised capabilities absent from this code chunk. Therefore the description does not accurately represent what this specific code chunk actually does.

Lp3

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding
Without declared permissions the skill's intent is opaque and cannot be validated.

Vague Triggers

Medium
Confidence
91% confidence
Finding
The activation cues are broad enough to match ordinary business conversation, which can cause the skill to trigger unexpectedly and access or manipulate sensitive local business records when the user did not intend to invoke it. In a privacy-sensitive skill handling client, revenue, and invoice data, overbroad routing increases the chance of inappropriate context capture or unintended file operations.

Static analysis

No suspicious patterns detected.