Ae4
Medium
- Category
- analysis-evasion
- Confidence
- 80% confidence
- Finding
Suspicious Unicode normalization or mixed-script content
- Content
Security audit
智能词汇DNA系统
Security checks for vulnerabilities and agentic risk
Overview
This is a coherent Chinese K12 English vocabulary review skill with disclosed profile storage and reminder queuing controls, and I found no hidden executable or deceptive behavior.
Install this only for the intended Chinese K12 English-learning context. Before enabling profile storage, reminders, or cross-skill sharing, confirm the relevant consent settings, guardian requirements for younger students, and localized emergency resources if used outside Mainland China.
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
- 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
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (7)
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
Several trigger phrases are broad everyday expressions such as '帮我记单词', '帮我复习词汇', and especially '我的词汇库里有什么', which can plausibly appear in normal conversation outside an explicit invocation context. This can cause unintended activation, leading the skill to access, display, write back, or enqueue reminders involving a user's vocabulary data when the user may not have meant to invoke this specific skill.
- Content
Ae4
Medium
- Category
- analysis-evasion
- Confidence
- 80% confidence
- Finding
Suspicious Unicode normalization or mixed-script content
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The document is entirely written in Chinese and framed as a core reference resource for the English-subject skill package, with no indication that users can opt into another language or locale. This creates a natural-language policy concern because it effectively imposes a specific language experience without documented user choice or a clear locale-specific justification.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The entire shared guidance is written as mandatory operating policy in Chinese and does not indicate that the user may choose another language or that the skill is limited to a Chinese-language educational context. Under the policy rule, forcing a specific language or locale without opt-in is a natural-language policy violation.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
Lines L11-L17 state that the repository is designed for Mainland China Chinese K12 scenarios, with simplified Chinese examples and China-mainland default safety resources. This is a natural-language locale policy constraint that forces a specific language/region unless operators localize first, rather than offering end users a language or locale choice.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
The file presents all instructional content in Chinese and does not indicate that the user 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 can be a natural-language policy concern.
- Content
Static analysis
No suspicious patterns detected.