Back to skill

Security audit

全球股市资讯

Security checks for vulnerabilities and agentic risk

Overview

This skill generates a Chinese daily stock-market report from public web searches and saves it as a Markdown file; its behavior is disclosed and purpose-aligned.

Install this if you want a Chinese daily global stock-market report saved to your Documents folder. Review the trigger phrases and output path first, especially if you prefer reports returned inline or in another language.

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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill advertises very broad trigger conditions such as generic market-analysis requests and references to "每日动荡," which can cause it to activate in situations where the user did not clearly intend this specific workflow. Because the skill performs autonomous web collection and file writing, overly broad invocation increases the chance of unexpected execution and unintended data retrieval or persistence.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill instructs the agent to create directories and write a Markdown report directly into the user's Documents folder without any explicit user-facing notice or confirmation. Silent filesystem writes are dangerous because they can create persistent artifacts the user did not knowingly authorize, and broad skill activation makes accidental writes more likely.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

Line L81 states '报告使用简体中文', which forces a specific language for all outputs. Under the language/locale policy, this is a natural-language policy violation unless the skill offers opt-in language selection or clearly documents a justified region-specific constraint.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The entire report template is written in Chinese and prescribes Chinese section headers and content structure, but the file does not indicate that this skill is region-specific or that users may choose another language. This creates a natural-language locale constraint that could violate organizational language-choice policy.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The manifest uses a Chinese display name and specifies generation of a named markdown report in Chinese, but does not mention any user language preference or opt-in. This can indicate a language/locale policy issue because the skill appears to force a specific language rather than offering a choice or documenting a justified regional scope.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger phrases are generic market/news terms such as '全球行情速览' and '市场变动分析', which can match ordinary user requests outside the intended narrow workflow. This can cause unintended invocation of the skill, potentially overriding user intent or causing the agent to collect and generate financial analysis when the user only requested a general discussion.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

Line L35 states '报告语言使用简体中文', which forces a specific language for the skill output. Under the policy, language constraints should either be optional for the user or clearly justified as region-specific; this file provides neither.

Content

No source excerpt is available for this finding.