Tp2
High
- Category
- MCP Tool Poisoning
- Confidence
- 85% confidence
- Finding
Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.
- Content
Security audit
Concept Anatomy
Security checks for vulnerabilities and agentic risk
Overview
This is a Chinese-language concept-learning framework with broad activation phrases, but it does not request tools, credentials, persistence, network access, or local data access.
Install this if you want Chinese-language structured concept analysis. Be aware it may activate on broad phrases like '搞懂' or '帮我理解', so users who prefer short answers or another language may need to be explicit.
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
- MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (7)
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
This markdown file consists entirely of Chinese instructional content and examples, with no indication that users can choose another language or that the skill is intentionally restricted to a Chinese-speaking context. Under the policy, forcing a specific language without user opt-in is a natural-language policy concern.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
This markdown file presents all skill instructions and operating guidance exclusively in Chinese, including headings, process steps, and trigger conditions. Under the policy rule for natural-language violations, forcing a specific language without user choice is a locale/language policy concern.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The trigger list includes broad everyday phrases such as '搞懂' and '学懂', which can appear in many unrelated user requests. That can cause unintended skill activation, leading the agent to apply this skill outside its intended scope and potentially override a more appropriate or safer workflow.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
The trigger table treats generic phrases like '深入理解 [概念名]' and '帮我理解' as sufficient activation conditions without strong constraints. This increases accidental invocation risk and can route ordinary explanatory questions into an unnecessarily opinionated reasoning workflow, affecting behavior selection and response quality.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 83% confidence
- Finding
The file centers activation and usage around Chinese trigger phrases and Chinese-language instructions, but does not state that users may invoke or receive the skill in other languages. This can be a language/locale policy concern when a skill implicitly forces one language without opt-in or explicit justification.
- Content