Back to skill

Security audit

胡田 OPC导师 苏轼 心智模型

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language Su Shi perspective skill made of static Markdown guidance, with no hidden code, persistence, credential use, or data access.

Install this if you want Chinese-language, Su Shi-inspired reflective guidance. Do not treat it as mental health, legal, financial, or crisis advice; ask for that historical perspective explicitly when you want it.

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)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill description and usage instructions are entirely presented in Chinese, with no indication that users may choose another language or that the skill is intended only for a Chinese-speaking or region-specific context. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The invocation guidance is framed around very broad, common life situations such as career setbacks, confusion, or work-life balance, which can cause the skill to activate in many unrelated user conversations. This increases the chance of over-triggering and steering users into a specific persona-based framework even when the user did not explicitly ask for it, creating scope creep and potentially inappropriate advice in sensitive contexts.

Content

No source excerpt is available for this finding.