Security audit

财务月度自查包（免费版）

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local Chinese-language financial table checker with limited disclosed checks and no evidence of network access, persistence, or hidden data handling.

Install only if you want a local Chinese-language checker for the listed finance table formats. Do not treat it as a general accounting, tax, audit, reimbursement approval, or filing tool, and pay attention to the free-tier checks_not_run list before relying on a clean result.

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
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

Findings (14)

Tp4

High

Category: MCP Tool Poisoning
Confidence: 96% confidence
Finding: The finding indicates the skill advertises a general-purpose monthly financial self-check capability but in reality performs a specialized travel-expense reimbursement review requiring very specific columns. That mismatch is dangerous because users may trust the branding and run unrelated financial materials through the skill, incorrectly believing broad reconciliation and original-text citation requirements were satisfied.
Content: No source excerpt is available for this finding.

Tp4

High

Category: MCP Tool Poisoning
Confidence: 94% confidence
Finding: The finding indicates the skill advertises a general-purpose monthly financial self-check capability but in reality performs a specialized travel-expense reimbursement review requiring very specific columns. That mismatch is dangerous because users may trust the branding and run unrelated financial materials through the skill, incorrectly believing broad reconciliation and original-text citation requirements were satisfied.
Content: No source excerpt is available for this finding.

Tp4

High

Category: MCP Tool Poisoning
Confidence: 97% confidence
Finding: The finding indicates the skill advertises a general-purpose monthly financial self-check capability but in reality performs a specialized travel-expense reimbursement review requiring very specific columns. That mismatch is dangerous because users may trust the branding and run unrelated financial materials through the skill, incorrectly believing broad reconciliation and original-text citation requirements were satisfied.
Content: No source excerpt is available for this finding.

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 41)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 42)May include surrounding context.
md
node scripts/run.mjs --sample # 先看样例

Intent-Code Divergence

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The result disclaimer states that a meal-allowance formula check is performed, but the free-version logic explicitly withholds that check. In a finance self-check context, this can mislead users into trusting a control that never ran, causing missed reimbursement overages or control failures during monthly review.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The user-facing name, summary, primary description, and trigger phrases are presented in Chinese, and the invocation examples are effectively Chinese-only. Although an English description exists, the skill does not state that users may choose their preferred language or that Chinese is required for a justified region-specific reason.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: This code file contains natural-language instructions, advice, notes, and disclaimers exclusively in Chinese, including the main header comment and returned user-facing messages. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is clearly documented and justified.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: This JavaScript file contains all major comments, prompts, advice, messages, and disclaimers exclusively in Chinese, including the primary user-facing outputs returned by the skill. There is no indication that the skill is region-specific or that users can opt into this locale, which creates a natural-language policy concern under the language/locale rule.
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 natural-language comments, sample text, prompts, and user-facing messages are entirely in Chinese, including the input instructions and output disclaimer. There is no indication that the skill is region-locked or that users may choose another language, which creates a language/locale policy concern under the natural-language policy rule.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: Nearly all user-facing strings, instructions, findings, and disclaimers in the skill are hard-coded in Chinese, including error messages and result text. This creates a language/locale policy issue if users are not explicitly opted into Chinese, because the skill provides no alternative locale selection or documented justification for the restriction.
Content: No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The manifest says the skill performs line-by-line recomputation, total reconciliation, duplicate and missing-value detection for monthly financial self-check materials in general. However, the file is explicitly scoped to travel reimbursement standards and checks travel-specific columns such as itinerary, trip dates, trip days, lodging, transport, meal allowance, and approval, which is narrower and materially different behavior than the manifest's generic finance self-check description.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Low

Category: Not specified by scanner
Confidence: 93% confidence
Finding: L075 的注释写明“不是 JSON 就当作纯文本材料（例如直接粘贴的合同全文）”，但该技能 manifest 与其余文档都将用途限定为财务月度自查/分段财务核对材料。代码本身确实会把任意非 JSON 文件整体作为 text 送入引擎，这与该注释中举的“合同全文”示例形成明显的意图层面偏离。
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The JSON text is entirely hard-coded in Chinese, indicating the skill output is fixed to a specific language/locale. The policy only allows this when the skill offers user opt-in or the locale constraint is clearly documented and justified, which is not present here.
Content: No source excerpt is available for this finding.