Security audit

摸摸头（PatPat）-你的科学育儿教练

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Chinese-language parenting guidance skill with safety triage instructions and no code, persistence, credential access, or external data handling.

Install this if you want a Simplified Chinese parenting-coach prompt pack. Treat it as general educational support, not medical, psychological, legal, or emergency help, and seek qualified professional or emergency support for self-harm, abuse, violence, severe withdrawal, or persistent impairment.

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
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 (9)

Vague Triggers

High

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The activation scope is explicitly broadened to trigger on nearly any family difficulty involving a parent or child, which can cause the skill to intercept many unrelated or higher-risk situations. In a parenting context, that is dangerous because it may overtake more appropriate system behavior, including specialized safety handling, mental-health escalation, or user-requested domains that only loosely resemble parenting concerns.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: This parenting skill targets sensitive child and adolescent scenarios, including emotional crises, school refusal, bullying, attention problems, and parent-child conflict, yet the README does not clearly state that the tool is not a substitute for licensed medical, psychological, or emergency support. In this context, users may over-rely on the assistant during situations involving self-harm risk, abuse, severe mental health symptoms, or developmental concerns, delaying appropriate professional intervention.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The policy states that all interactions, including content for children and parents, default to Simplified Chinese. This is a language/locale constraint expressed as a blanket default with no opt-in, alternative, or documented region-specific justification.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 78% confidence
Finding: The entire skill-facing document is written exclusively in Chinese and does not indicate that users may choose another language or locale. Under the policy, forcing a specific language without opt-in can be a natural-language policy violation unless the locale restriction is clearly documented and justified.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 86% confidence
Finding: The file is written entirely in Chinese and presents itself as the routing engine that should be consulted for every request, but it does not indicate that language selection is optional or configurable. This creates a natural-language locale constraint that could force Chinese outputs regardless of the user's preferred language.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The file presents all instructions and examples exclusively in Chinese and does not indicate that language selection is optional or configurable. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is clearly documented and justified.
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 appears to require Chinese for all user-facing guidance, starting from the title and core description, but does not state that the skill is China-specific or that users may opt into another language. Under the policy rule, forcing a specific language without user choice is a natural-language locale violation.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The entire skill specification is written as a Chinese-only interaction framework and repeatedly prescribes exact Chinese phrasing for responses, but nowhere indicates that language should be selected based on user preference. This creates a locale/language policy concern because the skill appears to enforce a specific language by default rather than offering user choice or documenting a justified regional constraint.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 85% confidence
Finding: A language/locale policy issue exists when a skill effectively forces a single language without stating that users may choose another language. This README consistently frames the skill in Chinese and does not mention multilingual support, user language selection, or that the Chinese-only scope is intentional and justified.
Content: No source excerpt is available for this finding.