Security audit

FinTech Risk Control Expert

Security checks for vulnerabilities and agentic risk

Overview

This is a single Markdown guidance skill for Chinese fintech risk modeling, with no executable installer, persistence, network behavior, or hidden privilege use.

Before using this skill with real credit, account, or customer data, remove unnecessary personal identifiers and confirm that any analysis complies with your organization’s privacy, lending, and model-governance requirements.

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 (3)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The skill explicitly supports analysis of financial data and credit risk, but it does not warn users about handling sensitive personal, financial, or regulated data. In this context, missing privacy and data-handling guidance increases the chance that users will submit raw PII, account data, or credit-related records without understanding retention, masking, minimization, or compliance implications.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger keyword list is broad and includes generic terms such as 风控, 决策树, 特征工程, and 风险评估 that can appear in many unrelated contexts. This can cause accidental invocation of a skill that handles financial-risk workflows, potentially leading the agent to process sensitive financial or personal data in situations where the user did not intend to use this specialized capability.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 88% confidence
Finding: L03 使用中文直接规定该技能的说明与交互定位，但未说明是否仅支持中文，也未提供语言选择或用户 opt-in。按照语言/locale 政策，若技能默认强制单一语言而无选择机制，可能构成自然语言策略违规。
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.