Security audit

BOM用量与损耗差异核对（免费版）

Security checks for vulnerabilities and agentic risk

Overview

This is a local BOM arithmetic checker with some scope wording to read carefully, but I found no hidden network, persistence, or destructive behavior.

Install only if you want a local arithmetic checker for Chinese-language BOM/work-order worksheets. Do not rely on the free version for 串料 detection, substitution approval checks, refund-not-offset checks, or overuse attribution; review the checks_not_run output before using results for accounting or audit decisions.

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)

Description-Behavior Mismatch

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The manifest says the free version only performs engine-declared free checks, but the surrounding documentation also advertises checks such as 串料 and other detections that are later explicitly excluded from the free version. This inconsistency can mislead users about the skill’s actual security and business-validation coverage, causing them to rely on missing controls and make incorrect operational decisions.
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 62)May include surrounding context.
md
node scripts/run.mjs --sample # 先看内置样例

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 63)May include surrounding context.
md
node scripts/run.mjs --sample # 先看内置样例

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 64)May include surrounding context.
md
node scripts/run.mjs --sample # 先看内置样例

Intent-Code Divergence

High

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The inline documentation claims the free version does not include certain detections, while earlier sections and trigger text imply those detections are part of the tool’s behavior. Contradictory statements about what is and is not checked undermine trust in results and can cause users to miss fraud, misallocation, or process-control issues they believed were being detected.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The manifest description says the skill is triggered by phrases including “工单超耗”, “损耗率算错”, and “领料与退料对不上” without defining invocation boundaries or exclusion cases. These are common problem statements in the domain rather than clearly scoped commands, so they risk unintended activation when users are merely discussing an issue instead of requesting this specific skill.
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 extensive natural-language instructions, descriptions, and output text in Chinese only. Because the file does not offer user opt-in for language selection or explain that the skill is intentionally region-specific, it effectively forces a specific language/locale.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The JSON content consists entirely of Chinese headers and data, indicating a fixed language/locale with no natural-language indication that users can choose another language. Under the policy rule, locale-specific behavior should be opt-in or clearly justified as region-specific.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The primary user-facing descriptions and trigger phrases are entirely in Chinese, and the file does not state that users may interact in other languages or choose their preferred locale. That can amount to a language-policy issue if the organization expects skills not to force a specific language without opt-in.
Content: No source excerpt is available for this finding.