Back to skill

Security audit

prediction-tendency

Security checks for vulnerabilities and agentic risk

Overview

This skill is a plain Markdown instruction set for manually supplied lottery-history statistics and does not show hidden execution, credential use, persistence, or destructive behavior.

Install only if you are comfortable using a Chinese-language lottery statistics helper. Treat outputs as historical summaries only, not predictions or gambling advice, and verify any lottery data you provide because the skill relies on manually supplied inputs.

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
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The entire skill description, usage guidance, and output example are written exclusively in Chinese, and the sample output is also fixed to Chinese phrasing. There is no indication that users may choose another language or that the skill is intentionally restricted to a Chinese-speaking or region-specific deployment, which creates a language/locale policy concern.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The skill description at L017 states it supports daily '录入/采集' of mainstream lottery winning numbers, which includes collection/acquisition behavior. Later, the usage notes at L140 explicitly say the skill has '无自动采集开奖数据功能' and requires manual input, creating an internal documentation contradiction about whether data collection is implemented.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.