Security audit

01 Complaint Classification

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only complaint-classification skill whose sensitive data handling and internal-business recommendations are aligned with its stated purpose, though users should treat it as advisory and protect complaint data.

Install only for internal complaint-triage use. Treat its output as routing and prioritization advice, not final liability or penalty authority, and redact personal, order, and account data unless your organization has approved handling and retention controls.

A.I.G

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

SkillSpector

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 (5)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: This markdown file contains example inputs with potentially sensitive user data such as an order number and high-value purchase details, and the surrounding description presents the file as a training/testing corpus. Under the markdown-specific warning rule, the document should disclose privacy or data-handling implications when user data may be included or processed, but no such warning appears in the file.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 79% confidence
Finding: This rules manual is written entirely in Chinese and contains no indication that language choice is optional or that the skill is restricted to a Chinese-only operating context. Under the policy criteria, forcing a specific language without user opt-in can be a natural-language policy violation unless the locale restriction is explicitly documented and justified.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: 该文件是 markdown，因此需要检查 vague triggers。L040-L043 将触发条件定义为“一段投诉文字”“一个投诉工单号”“一批投诉清单”，范围非常宽，几乎覆盖任何与投诉相关的自然表达，但没有给出更具体的触发短语、适用入口或负面示例，容易导致在普通对话中被意外调用。
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 95% confidence
Finding: All user-facing instructional and example content in the file is presented only in Chinese. Per the policy rule, forcing a specific language without user opt-in or a documented regional justification is a natural-language policy concern.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 61% confidence
Finding: SQP-3 关注自然语言层面的组织政策违规，包括强制性的语言或 locale/受众限制。该行写明“本 Skill 适用于内控人员使用，不对外（消费者）开放”，属于硬性受众限制说明，但未给出选择机制或更充分的约束上下文。
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.