Back to skill

Security audit

胡来给你算一卦

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Chinese-language entertainment fortune skill with no code execution, network access, persistence, or sensitive data handling.

Install this only if you want a Chinese-language novelty fortune skill. Expect it to respond in a fixed playful format and possibly activate on broad fortune-related or scene-related phrases; it should not need credentials, network access, or permissions beyond reading its bundled JSON data.

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
  • 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 (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger examples include broad everyday phrases such as '今日运势' and '测一测', which can cause unintended activation outside a clear divination context. In a conversational agent, overbroad triggers can hijack unrelated user requests and route them into this skill, degrading reliability and potentially interfering with safer or more relevant skills.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The scene-based routing maps very common topics like delivery, exams, overtime, and dieting to this skill without defining strict activation boundaries. That ambiguity increases the chance that ordinary user discussions about those topics will be misinterpreted as requests to invoke the fortune feature, causing unintended skill takeover and confusion.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

L93 要求“解读风格应轻松幽默,符合年轻人的网络用语习惯”,结合全文中文触发词与固定中文响应模板,实际形成了默认中文输出约束,但没有说明可根据用户语言偏好切换。这可能构成语言/locale 方面的自然语言政策问题。

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

This JSON file’s user-facing content is entirely in Chinese, including all fortune labels and interpretations, with no indication that the skill offers language choice or that it is intentionally limited to a Chinese-speaking context. Under the stated policy, forcing a specific language without opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.