Back to skill

Security audit

周期定位师

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only economic-cycle analysis skill with no code execution, persistence, credential access, or hidden data movement, though its investment guidance should be treated as educational rather than personal financial advice.

Install only if you want Chinese-language educational macroeconomic-cycle analysis. Do not use the allocation labels as personalized investment, tax, legal, or trading advice; verify current data, country assumptions, and suitability with a qualified professional before acting on any portfolio decision.

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 (7)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The entire README is written in Chinese, including headings and usage guidance, with no indication that language selection is optional or that the skill is intentionally limited to a Chinese-speaking context. Under the policy criteria, forcing a specific language without user opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill description uses broad triggers such as when a user wants to know the current economic cycle or make asset-allocation decisions, but it does not define clear exclusions or escalation boundaries. This can cause over-activation in general financial conversations and lead the agent to provide authoritative macro and allocation guidance in contexts where the user may need personalized, regulated, or higher-safety financial advice.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill provides concrete asset allocation recommendations tied to macro-cycle outputs, but the warning language is weak and does not clearly state that the content is general information rather than personalized financial advice. In practice, users may rely on these outputs for real investment decisions, creating a meaningful risk of financial harm, especially because the suggested allocations appear prescriptive and structured.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The example content is entirely in Chinese and does not provide any indication of language selection, localization fallback, or user-locale awareness. In an agent skill, hard-coding a single language can cause misinterpretation of financial guidance, exclude users who cannot read the content, and increase the chance of unsafe decision-making if users rely on misunderstood asset-allocation advice.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

This markdown file presents all skill content in a single language, which can constitute a language/locale policy violation when no user opt-in or alternative language support is provided. The file does not indicate that the skill is region-specific or that Chinese is an intentional, documented requirement.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The entire skill, including metadata, inputs, outputs, and examples, is written in Chinese and presents fixed Chinese-language enums and labels. There is no statement that the skill is China-specific or that users may choose another language, which may violate language/locale choice policy.

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 presents all headings, labels, and guidance exclusively in Chinese. Under the policy rule, forcing a specific language without offering the user a choice or documenting a justified locale constraint is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.