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
🇧🇷 巴西市场政策查询Skill
Security checks for vulnerabilities and agentic risk
Overview
This is a small Brazil trade-policy lookup skill with no bundled code, credentials, or hidden data access, though users should verify policy answers against official sources.
Installers should treat this as a reference aid for Brazil trade-policy questions, not legal or customs advice. Because the artifact promises current policy information without describing data sources, verify important tariff, licensing, or compliance answers against official Brazilian or customs notices before acting.
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 (3)
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
The example invocation "查关税政策" is very broad and could match many generic requests about tariffs or policy, without clarifying the boundaries of when this specific skill should activate. The document does not provide negative examples, exclusion conditions, or a narrower trigger scope to reduce unintended invocation collisions.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 77% confidence
- Finding
SQP-3 applies to all file types and covers language or locale policy violations. The manifest states "多语言支持" (multilingual support) but does not indicate that users can choose their preferred language or opt in to a specific locale, creating a risk that the skill may force language behavior without explicit user choice.
- Content