Security audit

存货盘点差异与账实调整核对（免费版）

Security checks for vulnerabilities and agentic risk

Overview

This is a local inventory-count reconciliation checker with disclosed limits and no evidence of hidden network, credential, persistence, or destructive behavior.

Install only if you are comfortable using a Chinese-language local CLI checker for pasted inventory count tables. Treat it as an arithmetic and completeness aid, not as accounting advice, audit evidence, ERP/WMS reconciliation, or a complete variance-control review; the free version explicitly omits several higher-level checks.

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)

Tp4

High

Category: MCP Tool Poisoning
Confidence: 96% confidence
Finding: The skill advertises capabilities that are stronger or more specific than what the implementation reportedly delivers, including claiming every conclusion cites original text and implying broader 'missing item' detection than simple blank/placeholder checks. In a business/accounting workflow, this can mislead users into overtrusting the output, potentially causing incorrect reconciliation decisions or missed discrepancies because users believe a stronger validation occurred than actually did.
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 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: 91% confidence
Finding: This is a code file, so SQP-3 applies to natural-language content in comments and string literals. The skill consistently describes usage, warnings, and user-facing advice exclusively in Chinese, with no indication that users can choose another language or that the locale restriction is 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 user-facing description, usage text, errors, and output strings are entirely in Chinese, which imposes a specific language/locale on users. The file does not indicate that the skill is region-specific or provide any opt-in or alternative language choice, which matches the language/locale policy-violation criteria.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 84% confidence
Finding: Nearly all user-facing instructions, examples, and operational guidance are presented only in Chinese, while the English text is minimal and does not provide equivalent usage guidance. This can constitute a language-policy issue when a skill implicitly forces a specific language without an explicit opt-in or a documented region-specific constraint.
Content: No source excerpt is available for this finding.

Vague Triggers

Low

Category: Not specified by scanner
Confidence: 77% confidence
Finding: The description says the skill is triggered by phrases including “存货盘点差异与账实调整核对” and “存货盘点表对不上.” The second phrase is conversational and could plausibly overlap with ordinary user complaints about inventory mismatches, while the file provides no negative examples or explicit scope boundaries for when the skill should not activate.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Low

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The comment says non-JSON input is treated as plain-text material such as a pasted '合同全文' (full contract text), which implies a broader document-ingestion intent. But the manifest and the rest of the file consistently describe a skill specifically for inventory count table checking, requiring a stocktaking table with headers.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The only user-facing text in this manifest-like JSON value is entirely in Chinese, with no indication that the skill is region-specific or that users can opt into another language. Under the language/locale policy, hard-coding a single language without choice or justification is a natural-language policy concern.
Content: No source excerpt is available for this finding.