Back to skill

Security audit

sunzibingfa

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese Sun Tzu advice skill with broad activation wording, but it contains only disclosed Markdown guidance and no code, persistence, credential access, or data movement.

Install this only if you want Sun Tzu-style strategic advice, especially in interpersonal, workplace, leadership, negotiation, or competition contexts. Be cautious using it for sensitive personal, legal, medical, financial, or mental-health decisions, and remember that some tactics are adversarial or manipulative if applied uncritically.

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

High
Category
Not specified by scanner
Confidence
96% confidence
Finding

The activation triggers are extremely broad, covering generic 'how to' questions, dilemmas, decision support, interpersonal issues, and management topics. This can cause the skill to activate for a large share of ordinary conversations and override more appropriate domain-specific guidance, increasing the chance of misleading, manipulative, or context-inappropriate advice.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
78% confidence
Finding

The entire skill, including name, description, activation rules, and response guidance, is written as Chinese-only operating instructions, with no indication that the user may choose another language. This can constitute a language/locale policy issue because it implicitly constrains output language without opt-in or an explicit region-specific justification.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The body repeats a vague activation condition without defining when the skill must not activate, leaving boundary decisions to the runtime or model. In practice, this ambiguity can lead to accidental invocation in sensitive or unsuitable contexts, especially because the skill is framed around competition, influence, and interpersonal conflict.

Content

No source excerpt is available for this finding.