Security audit

Positive Parenting

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Chinese-language parenting guidance skill with safety boundaries and no code, network access, persistence, or local data access.

Install this as a Chinese-language parenting support skill, not as medical, mental-health, legal, or emergency help. For self-harm, violence, suspected abuse, severe withdrawal, or immediate danger involving a child, use local emergency services or qualified professionals rather than relying on the skill.

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

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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 (9)

Vague Triggers

High

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger condition is explicitly expanded to 'any family difficulty involving a child or parent,' which makes the skill eligible to activate for an extremely wide range of conversations. In an agent environment, this can cause inappropriate routing, overshadow safer or more specialized skills, and lead users to receive parenting guidance in contexts involving mental health, abuse, or crisis where a general coaching skill is not appropriate.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: This skill targets parenting scenarios involving minors, emotional crises, school bullying, anxiety, and family conflict, yet the README does not clearly warn that the tool is not a substitute for professional help or specify escalation paths for emergencies. In practice, users may over-rely on the assistant during high-risk situations such as self-harm risk, abuse, severe mental health crises, or immediate safety threats, delaying appropriate human intervention.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 98% confidence
Finding: Mandating Simplified Chinese for all interactions without checking user preference can create consent and accessibility problems, especially if the surrounding system or user is operating in another language. In safety-sensitive parenting situations, forcing a language can reduce comprehension, impair escalation to emergency help, and cause the model to miss or mishandle critical details.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The vision covers sensitive youth mental-health scenarios, including low mood, self-negation, and referral to professional care, but it does not clearly warn users that the skill is not an emergency, crisis, medical, or licensed mental-health service. In a parenting context, users may over-rely on the skill during urgent situations involving a child or adolescent, delaying appropriate emergency or clinical intervention.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 85% confidence
Finding: The file is written entirely in Chinese and includes a prescribed user-facing prompt at L245, but nowhere offers language selection or indicates the behavior is limited to Chinese-speaking users. That creates a natural-language policy concern because the skill appears to force a specific language/locale without user opt-in.
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 file contains user-facing instructional content exclusively in Chinese, and nowhere indicates that the user can choose another language or that the skill is intentionally limited to a Chinese-speaking audience. 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

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: This markdown file contains natural-language instructions exclusively in Chinese, and nowhere indicates that the skill is China-specific or that users can opt into the language. That creates a language/locale policy concern because the skill effectively forces a specific language without user choice.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 84% confidence
Finding: The natural-language instructions and product framing are fully Chinese-language, and the document does not indicate that language selection is optional or that the skill is intentionally limited to Chinese-speaking users. Under the language/locale policy, forcing a specific language without user opt-in can be a policy concern unless the restriction is clearly documented and justified.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 72% confidence
Finding: Natural-language policy issues apply to all file types, including markdown. This file presents all user-facing content exclusively in Chinese without documenting that the skill is region-specific or offering a language/locale choice, which can amount to forcing a specific language without user opt-in.
Content: No source excerpt is available for this finding.