Security audit

Budget Data Model Skills

Security checks for vulnerabilities and agentic risk

Overview

This is a static Chinese budget-schema reference that can help draft database queries, with no bundled code, credentials, network payloads, persistence, or hidden behavior.

Install only if you need a Chinese-language budget-system schema reference. Before using generated queries against real budget or finance data, confirm you are authorized, keep queries narrow, avoid exporting unrelated bulk data, and review scripts before execution.

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
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (4)

Missing User Warnings

Medium

Confidence: 89% confidence
Finding: The skill explicitly encourages users to write and run budget-data queries, including raw SQL examples, but provides no guidance on access control, least-privilege use, sensitive financial data handling, or validation/review before execution. In a budget system context, this increases the chance of overbroad data exposure, unsafe query construction, or misuse of confidential business data by downstream agents or users.

Natural-Language Policy Violations

Low

Confidence: 95% confidence
Finding: The manifest description and the entire skill content are written in Chinese, and the guidance explicitly requires Chinese variable names. There is no indication that the skill is intentionally region-specific or that users may choose another language, which can violate language/locale policy requirements.

Natural-Language Policy Violations

Low

Confidence: 88% confidence
Finding: This manifest uses Chinese-only natural-language metadata in the description and keywords, which can amount to a language/locale constraint for discovery and use without any opt-in or documented regional justification. The policy requires flagging language or locale restrictions when they are imposed without offering user choice.

Natural-Language Policy Violations

Low

Confidence: 93% confidence
Finding: This JSON file contains natural-language field and table labels predominantly in Chinese, such as at L00003-L00004 and throughout the file. Under the language/locale policy rule, forcing a specific language without user opt-in or documented justification can be a policy violation, and no such justification is present in this file.

Static analysis

No suspicious patterns detected.