Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 78% confidence
- Finding
整个技能标题、说明、示例和触发词均固定为中文，未说明是否支持其他语言，也没有提供用户可选择语言/地区的选项。根据策略，若技能在自然语言层面强制特定语言而无用户选择或明确合理性说明，属于语言/locale 策略风险。
- Content
Security audit
Ai Project Pricing Cn
Security checks for vulnerabilities and agentic risk
Overview
This is a simple Chinese-language AI project pricing helper with no executable code, privileged access, persistence, or hidden data handling.
Before installing, treat its pricing numbers as advisory and verify current provider API prices and market rates, because model pricing changes over time. The broad trigger terms may also make it activate during general pricing discussions.
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
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The trigger list is broad and overlaps with common conversational/business terms such as '报价', '定价', and '成本计算', which increases the chance of unintended activation in unrelated chats. Mis-triggering can cause the agent to enter the wrong skill context, producing irrelevant outputs, interfering with expected workflows, or exposing downstream tools/prompts tied to the skill more often than intended.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 83% confidence
- Finding
The skill name, description, and tags indicate the skill is explicitly framed for Chinese usage, including the "chinese" tag, but the manifest does not state that this is optional or region-specific. This can violate language/locale policy when a skill appears to force a specific language without offering user choice or documenting a justified locale constraint.
- Content
Static analysis
No suspicious patterns detected.