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
Honest Game Guide
Security checks for vulnerabilities and agentic risk
Overview
This skill is a disclosed game-guide research prompt that uses web browsing for source verification and does not install code, persist data, or request unrelated access.
Install this if you want a Chinese no-spoiler game-guide assistant that searches and cites public sources. Be aware it may activate on broad game-related phrases, and it will browse external guide sites to verify answers.
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
- Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
- MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)
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
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
This manifest file includes trigger phrases, so SQP-1 applies. The phrase "隐藏内容" lacks constraints about game, task type, or invocation context, making it broad enough to match ordinary discussion and potentially cause unintended activation.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 88% confidence
- Finding
The trigger list is explicit, but this individual phrase is still vague because it can refer to many contexts and does not clearly limit activation to a specific game-guide workflow. Without exclusions or contextual constraints, it risks accidental invocation during ordinary conversation.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 77% confidence
- Finding
The natural-language instructions and required interaction flow are written to operate in Chinese, including mandatory first-response behavior and examples, but there is no explicit opt-in or language-choice mechanism. Under the policy, forcing a specific language or locale without user choice can be a violation unless justified or optional.
- Content
Static analysis
No suspicious patterns detected.