Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md - **示例**：更多使用示例请参考 `examples.md`
Security audit
获取各大平台热榜
Security checks for vulnerabilities and agentic risk
Overview
This skill is a disclosed HotRank Hub API wrapper for fetching public trending-list data, with no executable install code or hidden local authority found.
Install this if you are comfortable with your agent contacting airouter.tech to retrieve public trending-list data. For ambiguous requests like general news summaries, configure the agent to confirm whether HotRank Hub should be used, and avoid adding sensitive text to source IDs or custom API requests.
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
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- 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
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (11)
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
The natural-language content throughout the skill file is Chinese-only, including the description, headings, usage notes, and warnings. Under the language/locale policy rule, forcing a specific language without user opt-in or a documented region-specific justification is a policy concern.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 97% confidence
- Finding
The file presents the entire user guide, examples, and operational instructions only in Chinese, and does not offer an alternate language or indicate that the skill is intentionally limited to a Chinese-speaking or region-specific audience. This can violate language/locale policy when users are not given an opt-in choice.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The guide states that after installation, the agent can be called through broad natural-language requests and will 'automatically' invoke the skill. Without explicit activation constraints, common user requests about news or trending topics could trigger this external skill unexpectedly, causing unnecessary outbound requests and possible data flow to a third-party service. In agent ecosystems, vague trigger descriptions increase the risk of overbroad tool use and unintended invocation.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
The example trigger phrase '今天有什么热点新闻？' is ordinary everyday language that overlaps with many general assistant use cases. If the platform uses natural-language matching to select skills, this wording can cause the skill to auto-activate for broad requests that users may not intend to satisfy via this third-party API, increasing the chance of incorrect routing and unintended external calls.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 96% confidence
- Finding
SQP-3 covers natural-language policy violations across all file types, including forced language or locale constraints. This file presents all headings, explanations, and inline guidance in Chinese only, with no opt-in language selection or statement that the skill is intentionally limited to a Chinese-speaking or region-specific audience.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 87% confidence
- Finding
The manifest description and capability text are written entirely in Chinese, with no indication that the skill supports other languages or that it is intentionally limited to a Chinese-speaking audience. For a general metadata file, this can constitute a language/locale policy issue because it implicitly fixes the user-facing experience to one language without opt-in or justification.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
文件标题、说明、错误解释和使用指南均仅以中文提供，没有给出语言选择、双语版本入口，或说明该技能/文档为何必须限定中文。按规则，强制单一语言而无用户 opt-in 或明确地域性理由，属于自然语言层面的语言/locale 策略问题。
- Content
Missing User Warnings
Low
- Category
- Not specified by scanner
- Confidence
- 84% confidence
- Finding
这是 markdown 文件中的代码示例，明确执行
localStorage.setItem(...)将获取到的数据持久化到浏览器本地存储。文档将其作为“最佳实践”推荐，但没有任何用户提示说明数据会被保存在本地、保留时长或清理方式，属于对用户数据留存行为缺少披露。- Content
Missing User Warnings
Low
- Category
- Not specified by scanner
- Confidence
- 88% confidence
- Finding
This is a markdown file, so SQP-2 applies to whether the skill description warns about behaviors affecting privacy or system integrity. The document contains many examples using fetch, requests, and curl to contact https://airouter.tech, but it does not disclose that using these examples will send requests to a third-party service and may expose IP, headers, or queried source selections.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
This JSON manifest uses Chinese category labels, names, and descriptions throughout, which imposes a specific language/locale on consumers of the skill metadata. The file does not indicate that Chinese is optional, user-selectable, or justified as a region-specific configuration.
- Content
Static analysis
No suspicious patterns detected.