Security audit

Financial Fraud Analyzer Lite

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent financial-statement risk analysis helper; the reviewed code reads local financial data and calculates fraud-risk metrics without hidden persistence, exfiltration, or destructive behavior.

Install only if you are comfortable with a Chinese-first financial analysis workflow and verify the formulas/data paths before relying on outputs. Treat its conclusions as screening signals, not proof of fraud.

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

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (5)

Ae4

Medium

Category: analysis-evasion
Confidence: 80% confidence
Finding: Suspicious Unicode normalization or mixed-script content
Content: No source excerpt is available for this finding.

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 83% confidence
Finding: The skill instructs the agent to read local reference files such as references/beneish-formulas.md, references/industry-thresholds.md, and references/dechow-fscore.md, but it does not declare an explicit tool scope or permissions model. That mismatch can lead to over-broad file access at runtime or unclear trust boundaries, especially if the agent framework auto-enables file reads more broadly than intended.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The instruction '并始终保持' within an otherwise bilingual skill directs the agent to always follow the workflow in Chinese, and the file overall presents the operating instructions and output template exclusively in Chinese. This creates a language/locale constraint without offering the user a choice or documenting that the skill is intended only for a Chinese-language context.
Content: No source excerpt is available for this finding.

Ae4

Medium

Category: analysis-evasion
Confidence: 80% confidence
Finding: Suspicious Unicode normalization or mixed-script content
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: This Python file contains natural-language docstrings and console output exclusively in Chinese, including the module description and later user-facing messages. For a general-purpose skill, forcing a specific language without user opt-in matches the stated language/locale policy violation category.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.