Back to skill

Security audit

Industry Compare

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Chinese-language finance comparison helper with no evidence of hidden execution, exfiltration, persistence, or account-changing behavior.

Install only if you want a Chinese-language stock/industry comparison helper. Treat any investment suggestions or rankings as informational, verify market data independently, and do not provide a Tushare token unless you understand how the skill or future versions will use 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (8)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The phrase "你只管 do it" is very broad and reads like a generic invocation cue rather than a narrowly scoped activation condition. In a skill README, this kind of open-ended wording can blur when the skill should be used and may encourage unintended invocation in ordinary conversation.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The documented capability "投资建议生成" indicates the skill may produce investment-related guidance, which can materially affect user decisions. The README does not include any caution that outputs are informational only, may be inaccurate, or should not be treated as professional financial advice.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The trigger phrase "行业分析" is broad and likely to match many generic finance or market-analysis requests, causing the skill to activate outside narrowly intended scenarios. In an investment context, over-broad activation can surface opinionated financial comparisons or advice when the user did not explicitly request this specific tool, increasing the risk of misleading or unsuitable outputs.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The trigger phrase "公司对比" is ambiguous because it could refer to many kinds of comparisons beyond securities analysis, making unintended activation likely. When a financial-analysis skill activates on underspecified requests, it may generate investment-oriented framing or conclusions without sufficient user confirmation, which is risky in decision-support settings.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly lists "投资建议生成" as a core function but provides no warning that outputs are informational only, may be incomplete, and should not be treated as professional financial advice. This is dangerous because users may rely on generated recommendations for real monetary decisions without understanding limitations, data quality issues, or suitability constraints.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

All user-facing instructions and descriptions in the file are presented only in Chinese, which effectively forces a specific language experience. Under the policy, this should either offer a language/locale choice or clearly document that the skill is intentionally limited to a Chinese-speaking context.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The description and entire skill documentation are presented only in Chinese, with no indication that the user can choose another language or that the skill is intentionally limited to a Chinese-language audience. This can constitute a language policy issue when a specific language is effectively imposed without opt-in or documented justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The description, author, and tags are written in Chinese, which can impose a language-specific experience on users without any opt-in or justification. The policy requires either offering a language/locale choice or clearly documenting why the locale restriction is necessary.

Content

No source excerpt is available for this finding.