Back to skill

Security audit

转行创业顾问

Security checks for vulnerabilities and agentic risk

Overview

This skill is a Chinese-language career, skill-learning, and low-risk business validation guide with disclosed safeguards, not a tool that executes code, persists access, or performs hidden actions.

Install this if you want a Chinese-language guide for career changes, skill learning, freelancing, or small-business validation. Before relying on it, confirm your country/region, budget, and risk tolerance, especially for finance, regulated professions, health/safety services, and local business setup; treat investing content as education only, not advice to buy or sell anything.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (27)

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

声明描述的是一个职业与创业方向判断/学习规划类技能,核心能力应是分析用户目标、提供行业研究与训练建议、设计低风险实验并辅助复盘。代码却仅执行内部评测数据文件的格式与内容校验,属于开发/测试基础设施脚本。虽然 ALLOWED_MODES 中出现了与声明相似的中文标签(如“转行求职”“创业验证”),但这些只是被允许的CSV字段取值,不代表实现了对应用户功能。因此代码的主要目的与声明严重不符,应判定为明显不匹配。

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

This file adds a full personal stock investing and trading education module to a skill whose stated purpose is industry and career-path exploration. That scope expansion is dangerous because it can steer users into regulated, high-risk financial decision-making outside the skill’s declared function, weakening safety expectations and creating a pathway for harmful advice to appear under an unrelated skill surface.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The file does not merely mention finance; it operationalizes an investment/trading education capability with account opening, order types, market rules, chart reading, simulated orders, and research workflows. In the context of a career-exploration skill, this unjustified capability broadens the agent into advising on personally consequential financial behavior, increasing the chance of unsafe or noncompliant responses and user harm.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The README states the skill is '面向中文零基础用户', which sets a language-specific constraint in the natural-language description. Under the policy, forcing a specific language without user opt-in is a violation unless the locale constraint is clearly justified; this README does not provide such justification or offer an alternative language option.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The manifest description explicitly states the skill is for '中文零基础用户', which constrains the skill to Chinese-language use. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is clearly documented and justified as region-specific, which is not established here.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The file presents the skill example and continuation prompt exclusively in Chinese, which can amount to a language/locale policy violation when no user opt-in or alternative language option is provided. The content does not state that the skill is intentionally restricted to Chinese-language users or a China-specific compliance context.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

This markdown file contains user-facing guidance exclusively in Chinese across the entire document. Under the policy for natural-language violations, forcing a specific language without user opt-in can exclude users and should be documented or made optional.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The entire skill file is written only in Chinese and does not offer any language or locale choice to the user. Under the policy, forcing a specific language without opt-in is a natural-language policy violation unless the locale restriction is clearly documented and justified, which is not present here.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

All instructional content in the file is in Chinese, and there is no indication that the skill supports other languages or that Chinese is a justified region-specific requirement. This can violate language or locale policy when users are not given an explicit language opt-in.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger states the module runs when a user's goal includes broad categories like freelancing, personal branding, or entrepreneurship. This is ambiguous because many ordinary planning conversations could mention these goals, and the file does not provide exclusions or clearer scope constraints for when the skill should not activate.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This file forces a specific language/locale for all users through its natural-language instructions. Under the policy, language constraints should either offer user choice or be clearly documented and justified as region-specific, which is not present here.

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 skill-related evaluation document is written exclusively in Chinese and provides no indication that users or evaluators may choose another language or locale. Under the policy rule, forcing a specific language without opt-in is a natural-language policy violation unless clearly justified as region-specific, which is not stated here.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown file contains user-facing guidance exclusively in Chinese, and there is no indication that users may choose another language or that the skill is intentionally limited to a Chinese-speaking or region-specific audience. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

This markdown file contains all user-facing instructions in Chinese and does not indicate that the user can choose another language or that the skill is intentionally limited to a Chinese-speaking audience. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill instructs the agent to assume '中国大陆' when the user does not answer locale questions. For a career-path skill, region materially affects legality, licensing, labor market conditions, platforms, salaries, and business setup guidance, so silently defaulting can produce misleading or inapplicable advice for users in other jurisdictions.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
81% confidence
Finding

The file is entirely in Chinese and prescribes Chinese-language behavior without offering a language-choice mechanism or documenting why a Chinese-only restriction is required. In a multilingual agent, this can create mismatched outputs, reduce user comprehension, and undermine safety if important risk, compliance, or budget instructions are delivered in a language the user did not request or cannot fully understand.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The activation condition is very broad: phrases like “教我”, “怎么开始”, and “零基础入门” are common across many benign conversations, so this reference can be invoked far outside its intended scope. That can cause the agent to over-apply high-friction guidance, fetch unnecessary external information, or route users into domain-specific workflows when they only wanted a simple answer, increasing prompt-scope confusion and unintended behavior.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The file title and core instruction text are entirely in Chinese and direct the assistant on how to structure outputs, which implies a fixed language/locale behavior. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the constraint is explicitly justified or optional.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The file is written entirely in Chinese and frames the skill for Chinese-speaking use without stating that language is optional or user-selected. The policy requires flagging language or locale constraints when a skill forces a specific language without user opt-in, and no opt-in or explicit justification for Chinese-only operation is provided in these lines.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

Line L10 instructs the skill to provide a default version for '中国大陆、零基础、低预算' when information is missing. This imposes a mainland-China locale assumption without asking the user to confirm that locale, which is a natural-language policy concern because it may misapply region-specific guidance to users in other jurisdictions.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The entire skill instruction set is written as a mandatory Chinese-language workflow and does not indicate that the user may choose another language. Under the policy, imposing a specific language without opt-in is a natural-language locale violation unless the constraint is explicitly justified as region-specific.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The hard-coded ALLOWED_MODES values are all Chinese-language strings, which imposes a specific language/locale constraint in the validation logic. There is no nearby comment or docstring explaining that this is a region-specific or locale-bound tool, nor any indication of user choice or opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

SQP-3 applies to all file types and includes language or locale policy violations in natural-language text. Line L15 says the skill includes a Chinese description page for specific platforms, but this changelog does not indicate that language choice is optional or that the Chinese-only presentation is justified by a region-specific requirement.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

The natural-language guidance states a default of '中国大陆' for the user's situation, which imposes a locale assumption in the skill content. This can conflict with language/locale policy expectations when the user has not explicitly opted into a region-specific framing.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The progress card repeats '默认假设:中国大陆', reinforcing a specific regional default in the reusable prompt template. Because this is framed as the default operating assumption rather than a user-selected option, it constitutes a locale policy concern.

Content

No source excerpt is available for this finding.