Description-Behavior Mismatch
High
- Category
- Not specified by scanner
- Confidence
- 98% confidence
- Finding
该“商贸零售”技能的核心逻辑段落实际大量包含医美、肉毒素、玻尿酸、眼科等内容，与声明用途明显不一致。这会让代理在零售场景下输出错误行业框架，造成分析对象错配、结论失真，属于典型的技能内容污染/上下文混淆风险。
- Content
Security audit
AI Macro and Sector Master
Security checks for vulnerabilities and agentic risk
Overview
This markdown-only market-analysis skill has no executable malware behavior, but several reference files are mislabeled or polluted with unrelated sector content that could mislead investment analysis.
Install only if you are comfortable reviewing the reference files before relying on them. The main risk is not hidden code execution; it is that some templates can produce incorrect investment or market analysis because their content belongs to the wrong sector.
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
- 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
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (43)
Description-Behavior Mismatch
High
- Category
- Not specified by scanner
- Confidence
- 98% confidence
- Finding
产业链章节应服务于零售分析，但当前内容围绕医美上游药械、中游医美机构、下游胶原/MCN 变现展开，已实质偏离技能目标。若被代理直接采用，会把零售公司的供需、利润分配和定价权分析引向完全不同产业，显著降低输出可靠性，并可能误导投资或经营判断。
- Content
Description-Behavior Mismatch
High
- Category
- Not specified by scanner
- Confidence
- 99% confidence
- Finding
The file is labeled as a textiles/apparel analysis prompt, but its core logic, industry chain, KPI, and risk sections are populated with content from unrelated home appliance, panel, and black electronics sectors. This can cause the agent to generate materially incorrect investment or market analysis for the wrong industry, misleading users and undermining decision quality in a domain where factual sector fit is essential.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
The skill description is broad enough to trigger on many ordinary market or industry questions, which can cause the agent to activate this skill unexpectedly and override more appropriate default behavior or other specialized skills. In practice this creates scope confusion and can lead to unnecessary file reads, tool use, or policy/application of domain-specific guidance when the user did not explicitly request it.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 77% confidence
- Finding
The skill description and instructions are entirely in Chinese and describe a Chinese-market data/tool ecosystem, but do not indicate that the language is optional or based on user preference. This can amount to an implicit locale/language constraint without user opt-in.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 88% confidence
- Finding
The usage text says the skill should be used whenever users need to understand how to analyze an industry, market trend, or investment strategy, but does not define boundaries for when normal conversation should proceed without skill activation. That ambiguity increases the chance of over-triggering, making the assistant less predictable and potentially causing unnecessary access to reference files or external data skills.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The file’s natural-language instructions are entirely Chinese and do not indicate that users can choose another language or that the skill is intentionally limited to Chinese-speaking users. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 96% confidence
- Finding
This markdown skill forces a specific language for all instructions and outputs, but it does not provide any user opt-in, fallback, or justification for requiring Chinese. Under the policy rule, a language-only constraint is a natural-language policy violation unless the skill explicitly offers a choice or documents a justified regional limitation.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
The file is entirely written as mandatory Chinese-language instructions and repeatedly uses imperative phrasing such as '请严格按以下结构输出', which implies the skill will respond in Chinese by default. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is explicitly justified.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 96% confidence
- Finding
This markdown file contains instructions and required output formatting exclusively in Chinese, which effectively forces a specific language/locale for skill use. Under the policy, language constraints should either be optional or clearly justified; no such opt-in or justification is provided here.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
This markdown prompt file instructs the skill to operate in Chinese throughout, beginning with the title and all subsequent guidance, but it does not state that the user can choose another language. Under the policy rule, forcing a specific language without user opt-in is a natural-language policy violation.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 96% confidence
- Finding
The skill hard-codes Chinese-language role, framework, and output requirements across the entire file without any mechanism to respect the user's preferred language. This can override user intent, degrade usability, and cause downstream agent behavior to ignore language preferences or system-level localization expectations.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 96% confidence
- Finding
The file mandates a Chinese-language interaction format throughout the skill content and output structure, but it does not indicate that language selection is optional or user-configurable. This can violate language/locale policy requirements when users are not explicitly given a choice of language.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 96% confidence
- Finding
The skill content is entirely written in Chinese and includes mandatory output instructions such as '输出格式（强制）' without offering the user any language choice or opt-in. This can override user preferences, reduce transparency for non-Chinese-speaking users, and create a prompt-level policy conflict where the model follows the skill’s language constraint instead of the user’s requested language.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 96% confidence
- Finding
The entire skill is written as prescriptive output guidance in Chinese and instructs the model to respond according to that format, but it does not provide any option for the user's preferred language or locale. This is a natural-language policy concern because it imposes a specific language by default rather than offering user choice or documenting a justified locale restriction.
- Content
Description-Behavior Mismatch
Medium
- Category
- Not specified by scanner
- Confidence
- 96% confidence
- Finding
The fixed-income skill is materially contaminated with Fibonacci/technical-analysis content that does not match a general bond research framework. This can mislead downstream analyses toward pseudo-quantitative or irrelevant conclusions, reducing reliability and potentially causing poor investment or risk decisions when users expect sound fixed-income methodology.
- Content
Description-Behavior Mismatch
Medium
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
Modeling bond analysis as an upstream/midstream/downstream industry chain is a category error for most fixed-income use cases and can steer the agent into irrelevant equity-style reasoning. In context, this creates systematic analytical drift rather than a one-off wording issue, making the skill unsafe for users seeking bond or rates research.
- Content
Description-Behavior Mismatch
Medium
- Category
- Not specified by scanner
- Confidence
- 97% confidence
- Finding
The key dimensions, KPIs, valuation methods, and mandated output format are largely designed for listed-equity company research, not fixed-income analysis. Because the skill instructs the agent to produce structured outputs on company moat, share, PE/PB-style valuation, and stock-style catalysts, it can reliably generate incorrect or hazardous recommendations in a debt-analysis context.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The file is entirely written as a fixed Chinese-language prompt and instructs the model to follow that format when responding. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is explicitly justified, which is not present here.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
The entire skill is written as a mandatory Chinese prompt template and instructs the assistant how to respond, but it does not offer any language or locale opt-in for the user. Under the policy, forcing a specific language without user choice is a natural-language policy violation unless the regional constraint is explicit and justified.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
This markdown file contains natural-language instructions exclusively in Chinese, including the title, role definition, and required output structure. Under the policy, forcing a specific language without user opt-in is a locale/language policy concern unless the restriction is explicitly documented and justified.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 96% confidence
- Finding
This markdown file instructs the skill to operate in a single language throughout, from the title to the output requirements, without indicating that users may choose another language. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
The file title and core instructions are entirely in Chinese and specify the analyst role and output behavior in that language, but nowhere offer the user a language or locale choice. This creates a natural-language locale policy concern because the skill appears to require a specific language by default rather than making it opt-in.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 96% confidence
- Finding
The file is entirely written as a mandatory prompt template in Chinese and instructs the model to respond in a fixed format, but it does not offer the user any language or locale choice. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the regional constraint is explicitly justified.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 88% confidence
- Finding
This markdown skill instructs the agent in Chinese throughout and mandates a fixed output structure, but it never states that the user may choose another language or that the Chinese-only constraint is justified. Under the policy rule, forcing a specific language without opt-in is a natural-language policy concern.
- Content