Back to skill

Security audit

Apple HigDesign Skill

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only Apple design guidance skill with no executable install path or hidden data access, though users should note its Chinese-language defaults and illustrative sensitive-data examples.

Installers should treat this as a localized Apple design reference skill. It does not appear to run code or access data, but its broad triggers may make it appear in generic Apple discussions, and any generated HealthKit or device-sync code should be reviewed for user consent, privacy disclosure, and minimal data use.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (16)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill documentation is written entirely in Chinese, including headings, descriptions, and usage guidance, with no indication that users may choose another language or that the skill is intended only for a Chinese-speaking audience. This can violate language/locale policy because it imposes a specific language by default without opt-in or justification.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The trigger list contains broad terms such as Apple平台, watchOS, and tvOS, which can cause the skill to activate for generic platform mentions outside the user's actual intent. Overbroad activation can route unrelated conversations into this skill, degrading safety controls, causing policy misapplication, and increasing the chance of misleading or irrelevant guidance being injected into responses.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The output policy forces a single rigid response style and explicitly forbids certain structural formats without considering user preference or higher-priority system behavior. This can override user intent, reduce transparency, and create prompt-conflict conditions where the skill attempts to constrain the assistant's behavior too aggressively, making responses less adaptable and potentially less safe in edge cases.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The output guidance explicitly states '不要包含代码实现(那是 ios-dev 技能的职责)', indicating this skill should avoid code implementation content. However, the file itself includes multiple implementation-oriented code blocks for tvOS, watchOS, and animation APIs, which directly contradicts that stated intent and overlaps with development-focused behavior.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

This markdown file contains natural-language guidance exclusively in Chinese, starting with the section headings and continuing throughout the document. Under the stated policy, forcing a specific language without user opt-in can be a locale-policy violation unless the constraint is explicitly justified, which is not present here.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The instructional content and all user-facing examples are written entirely in Chinese, with no indication that the skill is intentionally limited to a Chinese-speaking context or that another language is available. Under the policy, forcing a specific language without user opt-in or clear justification is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

This markdown file includes HealthKit code that queries heart-rate data, which is sensitive user health information. The surrounding documentation presents the example without any warning about privacy implications, consent requirements, or the need to inform users before accessing health data.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

This markdown reference contains substantial Chinese instructional content alongside English headings and quotes, but it does not indicate that the skill is intentionally Chinese-only or provide a user language choice. Under the language/locale policy rule, forcing or implicitly assuming a language without opt-in can be a policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

The instructional content is presented entirely in Chinese, including headings, descriptions, and recommendations, with no indication that the skill is intentionally region-specific or that users may opt into another language. Under the policy, language constraints should either be justified or optional rather than implicitly enforced.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

This markdown reference is written in Chinese throughout, with no indication that language selection is optional or that the document is intentionally limited to a Chinese-speaking audience. Under the policy rule for natural-language constraints, forcing a specific language without user opt-in can be a locale-policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

This markdown reference is written entirely in Chinese, including labels, guidance, and example prompts such as "搜索", with no indication that the skill is intentionally limited to a Chinese-speaking audience or that users may choose another language. Under the stated policy, forcing a specific language without opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

This markdown file contains substantial content in Chinese alongside English terms and quoted English guidance, but it does not state the intended audience or give users an option for language preference. Under the natural-language policy rule, forcing or assuming a language/locale without opt-in can be a policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
97% confidence
Finding

This markdown file contains natural-language guidance entirely in Chinese, but it does not indicate that the user can choose another language or that the skill is intentionally region-specific. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

SQP-3 applies to all file types and includes language or locale policy violations. This markdown is primarily in Chinese but switches to English section headings and terminology such as 'Typography in visionOS' and 'Extra Large Title' without indicating that the user can choose a preferred language or that the mixed-language format is required.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

SQP-3 applies to all file types and covers language or locale policy violations. This markdown reference forces a specific language for all instructions and content, with no user opt-in, alternative language, or justification that the skill is intended for a Chinese-only audience.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

The markdown includes a WatchConnectivity example that receives and sends data between the watch and phone. Although this is a normal platform capability, the documentation does not mention that transmitted content may include user data and should be disclosed and minimized where appropriate.

Content

No source excerpt is available for this finding.