Back to skill

Security audit

Family Conflict Mediator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple Chinese-language family conflict mediation helper with no hidden system access, but users should not rely on it for emergencies or abuse situations.

Install only if you want a Chinese-language helper for non-emergency family disagreements. Do not use it as a substitute for emergency services, domestic violence support, child protection, legal advice, or mental health crisis support.

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
  • 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 (4)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill handles family conflict, a safety-sensitive domain, but provides no warning, escalation criteria, or crisis-routing guidance. That omission can cause dangerous under-response when the user is actually describing domestic violence, child endangerment, suicidal intent, or other situations where de-escalation scripts are inappropriate and delay access to help.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger list is very broad and can activate on common, ambiguous family-related situations without clear limits on severity, age, or crisis exclusion. In a conflict-mediation skill, overbroad invocation is risky because users in abuse, self-harm, or emergency situations may receive ordinary mediation guidance instead of being redirected to urgent support.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill title and all user-facing guidance are presented only in Chinese, indicating the skill is designed to operate in a single language/locale with no visible option for user choice. The policy for this audit requires flagging language or locale constraints when they are imposed without opt-in or explicit justification.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The manifest description is so generic ('auto-generated skeleton') that it does not meaningfully constrain when the skill should be invoked. This can cause accidental or overly broad invocation, making it harder for users or orchestrators to understand the skill’s purpose and increasing the chance of misuse in inappropriate contexts.

Content

No source excerpt is available for this finding.