Back to skill

Security audit

HexaLotto 六爻奇门测彩

Security checks for vulnerabilities and agentic risk

Overview

HexaLotto is a disclosed entertainment lottery-divination skill that uses public lottery results and a local Python calculator, with no evidence of credential access, persistence, exfiltration, or destructive behavior.

Install only if you want a Chinese-language entertainment tool for lottery-themed divination. Treat all generated numbers as random entertainment, not betting advice, and be aware that generic phrases like '算一卦' or '排盘' may activate this skill unless the agent asks for confirmation.

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
  • 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 (7)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

This markdown file contains user-facing instructions only in Chinese, including the title, steps, and comments. Under the policy rule, forcing a specific language without user opt-in can be a natural-language policy violation unless the locale limitation is explicitly justified.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The invocation examples use very broad natural-language phrases like “帮我算一卦” and “起一卦”, which can plausibly appear in ordinary conversation and trigger the skill unintentionally. Because this skill initiates web_search/web_fetch behavior and produces gambling-related predictions, accidental activation can lead to unexpected tool use, confusing outputs, and inappropriate engagement in a sensitive domain.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger list includes broad phrases such as ‘算一卦’, ‘起一卦’, and ‘排盘’, which are not unique to lottery prediction and could activate this skill during unrelated divination or discussion contexts. Because the skill then directs the agent to perform web searches and process gambling-related content, accidental invocation can cause unintended external actions and misroute user requests.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

This section gives concrete lottery-number recommendation mappings and report formats that facilitate gambling-oriented outputs, while the referenced file itself contains no warning, risk notice, or harm-minimization guidance. In the context of a skill explicitly designed to predict lottery outcomes, the omission increases the chance of encouraging gambling behavior or misleading users into treating divination-style output as actionable betting advice.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The module title, description, CLI help, and generated report text are written entirely in Chinese, and the file does not indicate any user-selectable language or that the tool is intentionally limited to a Chinese-speaking/regional context. Under the policy rule for language or locale constraints, this is a natural-language policy issue because the skill effectively imposes a specific language without opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The README is entirely Chinese-language and does not indicate that the skill is region-specific or that users may choose another language. Under the language/locale policy, forcing a specific language without opt-in can be a natural-language policy issue unless the locale limitation is explicitly justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

All user-facing instructions, trigger phrases, prompts, and output examples are specified only in Chinese, with no indication that other languages are supported or that the user can choose a language. This creates a language/locale constraint that is not presented as optional or justified as a region-specific requirement.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.