Back to skill

Security audit

活出自己的答案

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese self-reflection and growth-coaching skill with broad personal-topic triggers, but it contains no code, hidden execution, external data access, or persistence mechanism.

Install this only if you want a Chinese-language reflective coaching framework to engage on personal growth topics. Avoid treating it as professional mental health, legal, medical, financial, or relationship advice, and be mindful that its broad triggers may make it appear in many personal conversations.

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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The README states the skill should be automatically invoked for a very broad set of topics like life confusion, relationships, self-exploration, reflection, emotions, boundaries, and major life choices. Overbroad triggers can cause the agent to activate in situations where the user did not request this framework, leading to inappropriate guidance in sensitive contexts and increasing the chance it crowds out more suitable skills or safety handling.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The activation description is extremely broad and covers many common personal topics such as confusion, relationships, emotions, life choices, and self-exploration. This can cause the skill to trigger in a wide range of ordinary conversations, increasing the chance it overrides more appropriate domain-specific skills or engages in sensitive guidance beyond its stated limits.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill metadata and content are written entirely in Chinese and imply Chinese-language operation without stating whether users may interact in other languages. This can create unsafe mismatches where users receive unsupported language behavior, misunderstand boundaries, or are routed into a skill they cannot effectively use.

Content

No source excerpt is available for this finding.