Back to skill

Security audit

方洪波思维视角 v2.0

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language management-perspective persona skill with no code execution, data access, persistence, or hidden privileged behavior.

Install only if you want a Chinese-language business-management persona. Be aware that generic management phrases may invoke it unintentionally, so explicit activation wording would be preferable.

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 (5)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger list contains broad business phrases such as ‘职业经理人’, ‘战略定力’, and ‘组织重构’ that are likely to appear in ordinary discussion, which can cause unintentional invocation of the skill. This creates prompt-routing ambiguity and may override user intent or inject this persona into unrelated conversations, especially in enterprise or management contexts where these terms are common.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger list contains very broad terms such as '职业经理人', '战略定力', and '组织重构' that are common across many normal business conversations. This can cause unintended activation of the persona in unrelated contexts, overriding user intent or injecting biased first-person roleplay where it was not requested.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The user-facing display name, description, and trigger phrases are entirely in Chinese except for one English alias, with no indication that users may choose another language. This can violate language-choice policy when a skill implicitly enforces one locale without opt-in or a documented regional justification.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The activation guidance only says how to activate the skill, but does not define when it must not activate, how to handle ambiguous mentions, or whether explicit consent is required. In a multi-skill or assistant setting, this ambiguity increases the chance of accidental persona switching and unreliable outputs in contexts that merely discuss the subject.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
96% confidence
Finding

This markdown file is entirely written in Chinese, including headings and test descriptions, with no indication that the skill is region-specific or that users may choose another language. The policy requires flagging language or locale constraints when they are imposed without user opt-in or clear justification.

Content

No source excerpt is available for this finding.