ClawHub
Back to skill

Security audit

lotto-agent

Security checks across malware telemetry and agentic risk

Overview

This is a coherent lottery assistant that stores local lottery records and can run user-configured scheduled tasks with optional OpenClaw notifications.

Install this only if you want an agent that keeps local lottery records and scheduled lottery tasks. Review any cron entry and notification target before enabling push messages, and use explicit lottery commands because the skill asks hosts to invoke it on broad lottery-related keywords.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (3)

Context-Inappropriate Capability

Medium
Confidence
85% confidence
Finding
The code can send arbitrary outbound messages through the openclaw CLI using task-generated content and configured destination identifiers. In a skill with no manifest or explicit trust boundary documentation, this creates a real data-exfiltration and unauthorized-notification capability if task results or message content contain sensitive information or if configuration is tampered with.

Vague Triggers

High
Confidence
96% confidence
Finding
The README mandates that the host must immediately invoke this skill whenever a message contains lottery-related words, which is an overly broad trigger policy. Broad auto-invocation can cause unintended execution on casual mentions, route user data into the skill without clear intent, and increase the chance of unsafe side effects such as task creation or data processing when the user did not actually request lottery actions.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The skill declares an extremely broad, highest-priority trigger on many common lottery-related words and instructs the agent to bypass general conversation whenever any appear. This can cause unintended invocation from incidental mentions, leading to context hijacking, incorrect tool execution, or user requests being routed into a transactional workflow they did not intend.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.