Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md | **SKILL** | 完成特定场景任务的完整能力封装，包含 `SKILL.md`、`mcp.json`、原子接口实现、原子组件实现 |
Security audit
Wxa Ai Mode Dev
Security checks for vulnerabilities and agentic risk
Overview
This is a documentation-only skill for WeChat Mini Program AI-mode development, with no executable payload or hidden behavior found.
Install this as a documentation/reference skill for Chinese-language WeChat Mini Program AI-mode development. Be aware that several referenced companion documents or helper skills are not included in the inspected package, so some workflows may require separate trusted resources.
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
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (4)
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md | **SKILL** | 完成特定场景任务的完整能力封装，包含 `SKILL.md`、`mcp.json`、原子接口实现、原子组件实现 |
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md | **SKILL** | 完成特定场景任务的完整能力封装，包含 `SKILL.md`、`mcp.json`、原子接口实现、原子组件实现 |
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 88% confidence
- Finding
The description and examples require Chinese-language artifacts such as “content 文本写法” and the document consistently mandates Chinese phrasing for prompts and templates, but does not state that this skill is limited to Chinese-speaking users or offer an opt-in language choice. This creates a natural-language policy concern because the skill appears to force a specific language/locale by default.
- Content