ClawHub
Back to skill

Security audit

Chance Dlt Predictor

Security checks for vulnerabilities and agentic risk

Overview

This is a self-contained DLT lottery analysis skill with no tools, persistence, install scripts, or hidden data access, though its English trigger terms are broader than its stated DLT scope.

Use this only as entertainment or mathematical reference for DLT. Do not treat generated numbers as improving your odds, verify current rules and prizes with official lottery sources, and be aware that generic English lottery prompts may activate this DLT-specific skill.

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
  • 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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The English trigger list includes broad terms like 'lottery', 'lottery prediction', 'number selection', and 'lottery strategy', which can activate this DLT-specific skill for generic gambling-related requests outside its stated narrow scope. That misrouting can cause the agent to deliver domain-specific betting guidance when the user did not request DLT, weakening scope controls and increasing the chance of inappropriate or policy-sensitive engagement.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The language policy states that the skill uses Simplified Chinese as the default and only switches to English if the user requests it. This imposes a specific language preference by default rather than offering a neutral choice or explicit opt-in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.