Security audit

项目挣值分析核对（免费版）

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local EVM worksheet checker with no evidence of network use, persistence, credential access, or hidden behavior.

Installers should expect a Chinese-language, local-only Node worksheet checker. It should be used on project EVM table text exported or pasted with headers, and its output is limited to the free checks it explicitly lists.

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 (9)

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 45)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 46)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: 85% confidence
Finding: The primary display name, summary, and main description are presented in Chinese, and the usage/instructional content is also Chinese-first, with no statement that the user may choose their preferred language. Although an English description field exists, the skill does not clearly offer a language or locale choice for interaction.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The trigger list includes broad generic terms such as “EVM”, “CPI”, “SPI”, and “项目绩效”, which can match many unrelated contexts beyond this narrowly scoped project earned-value checking skill. This can cause unintended invocation, leading to user confusion, wrong tool selection, and inadvertent processing of unrelated business content.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: This skill embeds its description, contract notes, and operational guidance in Chinese only, and later returns Chinese-only user messages as well. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is clearly justified.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The function returns Chinese-only advice text to users, and similar Chinese-only strings appear throughout result messages and notes. This enforces a single language at runtime without offering user choice, which violates the language/locale policy for general-purpose skills.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The user-facing description, usage text, errors, and status messages are all written exclusively in Chinese, with no indication that another language can be selected. Under the policy, forcing a specific language without user opt-in is a natural-language locale violation unless clearly justified as region-specific.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The JSON template contains only Chinese headers and labels in its natural-language content, which imposes a specific language/locale by default. There is no indication that the user can choose another language or that the template is intentionally restricted to a China-specific or Chinese-only context.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Low

Category: Not specified by scanner
Confidence: 89% confidence
Finding: L075 的注释说明“不是 JSON 就当作纯文本材料（例如直接粘贴的合同全文）”，但该技能的清单与其余文档都明确限定为项目挣值分析表/EVM 核对。这里不是单纯信息缺失，而是用与技能目的不一致的“合同全文”作为输入示例，主动传达了偏离技能范围的意图。
Content: No source excerpt is available for this finding.