Security audit

研发支出资本化与费用化划分核对（免费版）

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local Chinese-language accounting table checker with no network or persistence, but users should not treat its results as audit or compliance advice.

Install only if you are comfortable running a local Chinese-language Node checker on R&D expenditure tables. Treat output as an arithmetic screening aid, not audit, tax, or accounting advice; verify inputs include all relevant columns, especially cumulative amortization, before relying on a no-issue 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

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 (9)

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: 89% confidence
Finding: The file provides nearly all operational instructions, boundaries, and usage details in Chinese, while the English description is minimal and does not give equivalent guidance. This creates a de facto language restriction without explicitly offering the user a language choice or documenting the locale limitation as a justified regional constraint.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The file’s user-facing descriptions, advice text, sample text, labels, and findings messages are entirely written in Chinese, with no indication that another language is supported or that the user can opt in to Chinese. This can violate language/locale policy when a skill implicitly forces a specific language without user choice.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The documentation says insufficient materials should prevent conclusions, but checkNetBook treats missing cumAmort as 0 and still emits arithmetic conclusions. In a financial-validation skill, this can produce materially misleading results from incomplete inputs, causing users to rely on incorrect compliance or accounting checks.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The user-facing description, help text, prompts, and output messages are entirely in Chinese, and the skill does not indicate that other languages are supported or that the user can choose a preferred language. 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.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The JSON value is entirely in Chinese and provides no indication that use of this language is optional, user-selected, or required for a documented region-specific purpose. Under the 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: 82% confidence
Finding: The file header states that CHECKS_WITHHELD is only descriptive text and not implementation. While the paid checks are indeed not executed, the code later returns checks_not_run: CHECKS_WITHHELD and exports CHECKS_WITHHELD, making that data part of runtime behavior rather than purely internal description text.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Low

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The inline comment says non-JSON input is treated as plain-text material such as '直接粘贴的合同全文', which conflicts with the manifest and surrounding code that consistently expect an R&D expenditure detail table with headers. This is an intent/documentation mismatch that could mislead users about acceptable input scope.
Content: No source excerpt is available for this finding.