Security audit

entropy-intimate-therapy

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language educational counseling framework with no executable code, persistence, credential handling, or hidden high-impact behavior.

Installers should treat this as a specialized Chinese-language educational aid for relationship-counseling concepts. It should not be used as a substitute for licensed therapy, clinical diagnosis, crisis response, medical advice, or legal advice; the artifact itself includes similar boundaries.

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

System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
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 (8)

Direct Prompt Extraction

High

Category: System Prompt Leakage
Content: 特别注意： - 跨文化伴侣：display rules（表现规则）不同 → 同信号在不同编码下解读不同 - 依恋类型不同的伴侣：同样的"沉默"在安全型是"思考"，在痴迷型是"威胁" 让双方明确：**我们用的是两套密码本**，需要相互翻译。
Confidence: 85% confidence
Finding: Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Natural-Language Policy Violations

Medium

Confidence: 95% confidence
Finding: Line L034 states '中文回答', which imposes a specific language policy on all interactions. The file does not indicate user opt-in, fallback behavior, or an option to respond in another language, so this is a natural-language policy violation under the language/locale rule.

Natural-Language Policy Violations

Medium

Confidence: 95% confidence
Finding: This markdown file presents all instructional and case content exclusively in Chinese, including the title, workflow, warnings, and closing usage guidance. Under the policy rule for natural-language violations, forcing a specific language without user opt-in or a documented justification is a reportable locale-policy issue.

Natural-Language Policy Violations

Medium

Confidence: 95% confidence
Finding: The entire skill file is written as Chinese-only instructional content, and it does not indicate that the user may choose another language or that the skill is intentionally restricted to a Chinese-speaking context. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.

Natural-Language Policy Violations

Medium

Confidence: 90% confidence
Finding: This markdown file contains substantial natural-language guidance but forces a specific language/locale throughout the document. Under the policy, language constraints should either offer user opt-in or be clearly documented as justified for a specific region or audience.

Natural-Language Policy Violations

Medium

Confidence: 97% confidence
Finding: This markdown file is entirely written in Chinese and does not provide any indication that language selection is optional or that the material is intentionally limited to a Chinese-speaking audience. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation.

Natural-Language Policy Violations

Low

Confidence: 95% confidence
Finding: The file is written entirely in Chinese and does not indicate any user language negotiation or justified locale restriction. In a user-facing skill, this can exclude users, cause misunderstanding of therapeutic content, and increase the chance that users misinterpret nuanced psychological guidance because they cannot access it in their preferred language.

Natural-Language Policy Violations

Low

Confidence: 91% confidence
Finding: This markdown skill reference appears to require Chinese comprehension throughout, including headings, instructions, and examples. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is explicitly documented and justified.

Static analysis

No suspicious patterns detected.