Back to skill

Security audit

现金流预测与实际差异核对(免费版)

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local cash-flow table checker with no network use or persistence, though its documentation has language and feature-scope inconsistencies users should notice.

Install only if you are comfortable running a local Node-based checker on cash-flow table data and working with Chinese-language output. Review the documented free-version limits carefully, especially the inconsistent wording around negative inflow/outflow checks, and do not treat the output as broader financial validation beyond the arithmetic checks it lists.

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 (8)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 48)May include surrounding context.

md
node scripts/run.mjs --sample # 先看样例

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 49)May include surrounding context.

md
node scripts/run.mjs --sample # 先看样例

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The primary display name, summary, description, and usage content are written in Chinese, and the file does not state that the skill is limited to Chinese-speaking users or offer a language choice. Although an English field exists, the main user-facing guidance appears to require Chinese, which can violate language/locale policy when not documented as an explicit opt-in or regional constraint.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The feature list for the free version explicitly includes '金额为负检测(流入 / 流出都必须非负)' at L43. Later, the same document says the free version '不包含' '流入为负或流出为负(方向填反)提示' at L74 and again at L89, which is the same substantive check. These statements actively contradict each other about what the skill does.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The file’s user-facing natural-language documentation and operational guidance are entirely in Chinese, including warnings, scope, and usage instructions. This imposes a specific language/locale without any opt-in or alternative, which matches the policy-violation criterion for forced language use.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The user-facing description, help text, error messages, and outputs are entirely in Chinese, and the file does not indicate that language selection is optional or configurable. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
97% confidence
Finding

The comment says non-JSON input is treated as plain-text materials such as '直接粘贴的合同全文', which describes a broader document-ingestion use case unrelated to cash-flow forecast-vs-actual table checking. Elsewhere, the file consistently documents and enforces that the expected input is a cash-flow variance table with headers, so this inline documentation is contradictory rather than merely incomplete.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The only natural-language content in this file is a Chinese-language tabular template, which implies a fixed language/locale for skill output or sample data. Under the policy, locale-specific language should either be optional for the user or clearly documented as a justified regional constraint.

Content

No source excerpt is available for this finding.