Back to skill

Security audit

intimate-ch08-love

Security checks for vulnerabilities and agentic risk

Overview

This is a static Chinese-language study aid for one textbook chapter and does not request code execution, credentials, persistence, or broad local access.

Install this if you want a Chinese study helper for this specific relationship textbook chapter. Users who need another language or do not want relationship questions mapped into textbook concepts may need clearer language-preference and activation settings from the publisher.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (12)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The usage section is presented entirely in Chinese and gives no indication that users may choose another language or locale. Under the stated 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

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The file’s instructional and user-facing content is wholly in Chinese, and there is no indication that the skill is intentionally region-specific or that users can opt into another language. This creates a natural-language policy concern because it implicitly forces a specific language/locale without user choice.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

This markdown file presents all usage instructions and examples exclusively in Chinese, beginning at the section heading on L03 and continuing throughout the document. Under the policy rule, forcing a specific language without user opt-in or a documented justification is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

Line L05 states '先用中文解释,再给英文原词', which imposes a specific language order as a default behavior. Under the policy, forcing a language or locale without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger phrase 用户问“这属于哪种爱”时 is broad enough that the skill may activate on ordinary relationship discussions rather than only explicit textbook-help requests. In this educational context the consequence is limited, but unintended invocation can still cause context hijacking, user confusion, or disclosure of skill content when the user did not intend to use this lesson flow.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The file's operational instructions are entirely in Chinese and specify when the file should be used, but they do not indicate that language is optional or limited to a China-specific context. This creates a natural-language locale policy concern because the skill appears to assume a fixed language without user opt-in.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The usage section says to read this file when the user asks about romance, passion, infatuation, arousal, or idealization, which is a wide set of everyday topics. It does not provide boundary conditions or negative examples to clarify when this skill should not activate, increasing the risk of unintended invocation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The usage instructions are written as fixed Chinese-language behavior without offering a language-selection mechanism, which can override user preference or create confusing responses for users interacting in another language. While this is not a classic security flaw, it is a policy/routing weakness that can degrade user control and may cause the agent to ignore explicit user language context.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger 用户问"为什么会这样"时读本文件 is broad enough to match ordinary conversational phrasing, so the skill may activate or pull this reference in situations not specifically intended by the user. In a multi-skill or agentic setting, overly generic triggers can cause prompt-routing collisions, unnecessary disclosure of internal material, or behavioral hijacking of otherwise unrelated conversations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
96% confidence
Finding

Line L25 states '中文回答' as a fixed instruction, which imposes a specific language preference. Under the policy criteria, forcing a language without user opt-in is a natural-language policy violation unless the locale constraint is explicitly justified or optional.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

The instructional content is entirely in Chinese and gives usage directions only in that language, with no indication that the user can choose another language. This can conflict with a language or locale policy if the skill is expected to adapt to user preference unless a language constraint is explicitly justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The natural-language instructions and content are entirely in Chinese, which can effectively force a specific language behavior if the skill is used in a broader multilingual environment. There is no indication that users can opt into another language or that the Chinese-only constraint is required for a region-specific purpose.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.