Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md 把 `scripts/render.js` **和 `scripts/themes.js` 一起**复制到 HTML 同目录（两个文件缺一不可，渲染需要主题库），运行：
Security audit
小红书图文笔记生成
Security checks for vulnerabilities and agentic risk
Overview
This skill is a purpose-built local Xiaohongshu image-note generator with expected template, rendering, and copywriting files, and no evidence of hidden access, exfiltration, persistence, or destructive behavior.
Install this only if you want a Chinese/Xiaohongshu-focused content workflow. Expect it to run local Node/Playwright rendering, create PNG files under an export directory, and briefly create a temporary themed HTML file during rendering.
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
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (8)
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md 把 `scripts/render.js` **和 `scripts/themes.js` 一起**复制到 HTML 同目录（两个文件缺一不可，渲染需要主题库），运行：
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The HTML root sets
lang="zh-CN", and all visible content is written in Simplified Chinese, which imposes a specific language/locale on users. Under the policy, locale constraints should either be optional for the user or clearly documented as region-specific and justified; this file provides neither.- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
This markdown guidance forces a specific language/locale in its natural-language instructions, which can violate organizational language-choice policies when no user opt-in is provided. The file does not indicate that Chinese output is optional or limited to a justified region-specific use case.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 80% confidence
- Finding
The file header comment is written entirely in Chinese and presents the skill purpose only in that language. Under the policy, forcing a specific language without opt-in can be a natural-language policy violation when no alternative or language choice is offered.
- Content
Missing User Warnings
Low
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
This code creates a temporary file (
_themed.html) on disk and later removes it, which is a file write/delete operation. While progress is logged for rendering, there is no visible warning, comment, or docstring disclosing that the script modifies files in the script directory before cleanup.- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
This JavaScript file includes natural-language comments and at least one user-facing console error message in Chinese, which imposes a specific language on users without any opt-in or locale selection. The stated policy flags forced language or locale choices across all file types unless they are explicitly justified or optional.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 98% confidence
- Finding
Line L88 emits a runtime error message only in Chinese, which is a natural-language policy concern because users receive enforced locale-specific feedback without opt-in. This is distinct from comments because it directly affects runtime interaction.
- Content