Security audit

云之家表单通用解析规则

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only skill for parsing and constructing YunZhijia form JSON, with some sensitive examples that users should handle carefully.

Install only if you work with YunZhijia form data. Before using generated approval payloads or file-download examples against a real tenant, confirm authorization, use least-privilege tokens, avoid logging tokens or personal identifiers, and review any generated request before submission.

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

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (7)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The README explicitly promotes building approval request data for a business workflow system, which can lead an agent or user to generate payloads that create or modify approval records without any warning about authorization, change control, or production impact. In an agent-skill context, omission of write-side safety boundaries is risky because the skill is positioned not just as a parser but as a constructor for state-changing requests.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The manifest description and document title/instructions are entirely in Chinese, and the skill does not indicate that users may choose another language or that the skill is intentionally restricted to a Chinese-speaking or region-specific audience. Under the policy, forcing a specific language without opt-in is a natural-language policy violation.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 87% confidence
Finding: This markdown file documents and exemplifies handling of personal data such as names, gender, employment date, and especially identity card numbers in the detailed widget payload and parsed output. The section provides no warning about sensitivity, masking, minimization, or privacy considerations, even though the examples could affect user data handling practices.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The documentation includes an explicit x-accessToken example value in a live-looking API request without any warning that the token is sensitive or must be redacted. Even if the token is illustrative, readers may copy insecure practices into production docs, logs, scripts, or support channels, increasing the risk of credential leakage and unauthorized file access.
Content: No source excerpt is available for this finding.

Vague Triggers

Low

Category: Not specified by scanner
Confidence: 84% confidence
Finding: The automatic trigger description is broad enough that the skill may activate for loosely related form-processing requests without clear exclusions, increasing the chance that an agent applies write-oriented transformation logic in the wrong context. While the README does not itself execute actions, ambiguous triggering in an automation setting can cause unintended handling of sensitive business form data or accidental preparation of submission payloads.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 77% confidence
Finding: A language-specific skill document can violate language or locale policy when it effectively forces one language without offering user choice or documenting a justified locale restriction. This file presents all instructions and examples only in Chinese and does not state that the content is region-specific or optional by language.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 88% confidence
Finding: This markdown file contains natural-language content exclusively in Chinese and does not indicate that the skill is region-specific or that users may choose another language. Under the language/locale policy criterion, forcing a specific language without opt-in can be a policy concern.
Content: No source excerpt is available for this finding.