Security audit

intimate-ch05-communication

Security checks for vulnerabilities and agentic risk

Overview

This is a scoped Chinese-language study skill for one textbook chapter and does not request dangerous access or hidden actions.

Install this if you want a Chinese-language study aid for this specific textbook chapter. It should not be treated as therapy, legal advice, or safety planning; if discussing abuse, coercion, or immediate risk, use appropriate professional or emergency support.

A.I.G

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

SkillSpector

Vulnerability Patterns

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
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)

Direct Prompt Extraction

High

Category: System Prompt Leakage
Confidence: 85% confidence
Finding: Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.
Content: Scanner excerpt · SKILL.md (reported line 3)May include surrounding context.
md
--- name: intimate-ch05-communication description: 在对话中辅助学习"亲密关系/Intimate Relationships"第 5 章"沟通"。基于 Rowland S. Miller《Intimate Relationships》教材第 6 版。（communication 沟通；interpersonal gap 人际隔阂；nonverbal communication 非言语沟通；display rules 表现规则；microexpressions 微表情；gazing 注视；self-disclosure 自我表露；social penetration theory 社会渗透理论；responsiveness 应答性；taboo topics 禁忌话题；active listening 积极倾听；validation 确认）使用渐进式披露，按需读取 references/ 下的细节，把课本知识自然引入学习对话 --- # Intimate Relationships 第 5 章：沟通

Direct Prompt Extraction

High

Category: System Prompt Leakage
Confidence: 85% confidence
Finding: Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.
Content: Scanner excerpt · references/key-terms.md (reported line 20)May include surrounding context.
md
--- name: intimate-ch05-communication description: 在对话中辅助学习"亲密关系/Intimate Relationships"第 5 章"沟通"。基于 Rowland S. Miller《Intimate Relationships》教材第 6 版。（communication 沟通；interpersonal gap 人际隔阂；nonverbal communication 非言语沟通；display rules 表现规则；microexpressions 微表情；gazing 注视；self-disclosure 自我表露；social penetration theory 社会渗透理论；responsiveness 应答性；taboo topics 禁忌话题；active listening 积极倾听；validation 确认）使用渐进式披露，按需读取 references/ 下的细节，把课本知识自然引入学习对话 --- # Intimate Relationships 第 5 章：沟通

Direct Prompt Extraction

High

Category: System Prompt Leakage
Confidence: 85% confidence
Finding: Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.
Content: Scanner excerpt · references/nonverbal-communication.md (reported line 15)May include surrounding context.
md
--- name: intimate-ch05-communication description: 在对话中辅助学习"亲密关系/Intimate Relationships"第 5 章"沟通"。基于 Rowland S. Miller《Intimate Relationships》教材第 6 版。（communication 沟通；interpersonal gap 人际隔阂；nonverbal communication 非言语沟通；display rules 表现规则；microexpressions 微表情；gazing 注视；self-disclosure 自我表露；social penetration theory 社会渗透理论；responsiveness 应答性；taboo topics 禁忌话题；active listening 积极倾听；validation 确认）使用渐进式披露，按需读取 references/ 下的细节，把课本知识自然引入学习对话 --- # Intimate Relationships 第 5 章：沟通

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The skill explicitly instructs the assistant to answer in Chinese, which can override or conflict with a user's language preference and reduce user autonomy. This is a policy/control issue rather than a classic security exploit, but it can cause misuse of the skill routing or poor handling of multilingual users if the framework expects user-directed language selection.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 84% confidence
Finding: This markdown file contains natural-language instructions exclusively in Chinese and provides no opt-in or alternative-language guidance. Under the policy rule, forcing a specific language without user choice can be a locale/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: The instructions and content explicitly prescribe Chinese as the operating language, including retaining English terms only on first explanation and using Chinese abbreviations thereafter. This is a natural-language locale policy constraint, and the file does not offer user opt-in or explain a justified region-specific need.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: This markdown file is entirely written as operational guidance in Chinese and presents no indication that the user can choose another language. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is explicitly justified.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The heading '使用方式' and the rest of the instructions are written entirely in Chinese, which imposes a specific language on the skill's behavior without offering user opt-in or alternatives. Under the policy criteria, a skill that forces a language or locale without choice is a natural-language policy violation unless the restriction is justified as region-specific.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: Lines L03-L08 are written as operational instructions and imply the skill should answer using Chinese-language guidance, but there is no indication that the user can choose another language. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless clearly justified as region-specific.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: This markdown skill content appears to force a specific language/locale for use, which can violate language-choice policy when no user opt-in or justification is provided. The file contains instructional content only in Chinese and does not indicate any optional language support or scope limitation.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The document presents the skill instructions entirely in Chinese, beginning with the section heading “使用方式,” with no indication that language choice is optional. Under the stated policy, forcing a specific language or locale without user opt-in is a natural-language policy concern.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The skill content is entirely written in Chinese and begins with a Chinese usage section, but there is no indication that language choice is optional or that the file is intentionally restricted to a Chinese-speaking context. Under the policy, a skill that effectively forces a specific language without user opt-in is a natural-language policy concern.
Content: No source excerpt is available for this finding.