Back to skill

Security audit

Daily Budget Skill

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Chinese-language budgeting helper that stores expense records locally and does not show hidden execution, network access, or privilege-seeking behavior.

Install only if you are comfortable keeping personal spending records in local Markdown files under ~/Documents/daily-budget. Treat the privacy wording as a documentation claim rather than a technical guarantee, and review exported CSVs before sharing them.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill name and full user-facing description are written only in Chinese and present the assistant as a Chinese-language budgeting helper, with no indication that users may choose another language. Under the policy, imposing a specific language without opt-in is a natural-language policy violation unless the locale constraint is clearly documented and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

This file presents all user-facing content exclusively in Chinese and does not mention that the language is optional or intended for a Chinese-only audience. Under the policy rule, forcing a specific language without user opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

The skill manifest describes a budgeting assistant, while this file is a social-media marketing document making a concrete product claim: '数据全在本地,不怕泄露'. Because there is no implementation here to substantiate local-only storage, the documented behavior in this skill artifact overclaims privacy characteristics not evidenced by code.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.