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
AIGC佬猫原创IP漫剧专家
Security checks for vulnerabilities and agentic risk
Overview
This is a prompt-only Chinese workflow for developing original AI comic-drama IP, with no evidence of hidden code, credential access, persistence, or destructive behavior.
Install this if you want a Chinese, step-by-step creative workflow for AI comic-drama IP development. Be aware it may activate on broad IP or comic-drama terms and will try to run a long staged process requiring “确认” or “修改” to proceed.
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
- 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
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The trigger list contains many broad, generic phrases such as 'IP研发', '漫剧创作', and 'IP开发', which can cause the skill to activate in conversations that only loosely relate to those topics. Unintended activation can override user intent, inject large amounts of prescriptive workflow text, and increase prompt-surface area for instruction conflicts or denial-of-service-style context flooding.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The interaction protocol is written as a mandatory requirement and requires explicit replies using the Chinese terms 「确认」 or 「修改」. This imposes a specific language on users without offering any language/locale choice or documenting a justified region-specific constraint.
- Content