Back to skill

Security audit

Huangdaxian Lingqian

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese fortune-telling prompt skill with no bundled executable code, credentials, persistence, or data access beyond normal conversation.

Install only if you want Chinese-language folk-divination responses. Treat outputs as entertainment or cultural reference, not as medical, financial, legal, or life-planning advice; broad phrases about luck, career, or relationships may activate it.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (6)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

All user-facing instructions and examples in the README are presented exclusively in Chinese, and the document does not indicate that language selection is optional or that the skill is intentionally limited to Chinese-speaking users. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The example trigger phrases are broad, natural-language requests such as asking about recent luck or career fortune, which can overlap with ordinary conversation and cause unintentional skill activation. In an agent environment, this can lead to the skill responding when the user did not explicitly intend to invoke divination behavior, increasing prompt-routing mistakes and unexpected outputs.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger list includes broad, everyday phrases such as '看看运势', '最近运气', and '问事业' that can match ordinary conversation unrelated to an intentional skill invocation. This can cause the skill to activate unexpectedly and steer conversations into fortune-telling content without clear user intent, increasing the risk of inappropriate routing or response hijacking.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The supported query examples include generic requests like '看看我的姻缘' and '最近事业如何', which are common conversational prompts that may be asked in many contexts. Because these examples define acceptable activation inputs, they blur the boundary between normal chat and deliberate skill use, making accidental invocation more likely.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

This markdown file presents all user-facing content in Chinese, including the title, descriptions, and instructions to consult external sites. Under the policy rule for natural-language violations, forcing a specific language without user opt-in can be a locale policy issue when no alternative or justification is provided.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The only natural-language content in this file is written in Chinese, which can indicate a language-specific constraint without any opt-in or explanation. Under the policy rule for language/locale violations, this should be documented as intentional or made optional for users who do not use Chinese.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.