Back to skill

Security audit

unsuck-your-thinking

Security checks for vulnerabilities and agentic risk

Overview

This skill is a Chinese-language thinking coach with broad conversational triggers, but it does not request tools, data access, persistence, or privileged actions.

Install this if you want a Chinese-language assistant style for clarifying uncertainty and decisions. Be aware it may activate for casual expressions of confusion, so users who want narrower or multilingual behavior may prefer a version with explicit opt-in triggers or language-matching guidance.

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 (2)

Vague Triggers

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill is configured to trigger on extremely common expressions like '帮我想想' and '我不知道该怎么办', and even states it must trigger when users say them. This creates broad overlap with ordinary conversation, making unintended activation likely and allowing the skill to hijack many unrelated interactions that merely express uncertainty.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The skill description and behavior are entirely specified in Chinese and target Chinese trigger phrases without any indication that language selection depends on user preference. This can force a language mode the user did not request, causing confusion, degraded UX, and incorrect activation behavior in multilingual settings.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.