Back to skill

Security audit

AI大模型专家|电商内容 API 平台替代方案|AI-HIVE

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed AI-HIVE migration planning skill with a local JSON helper script and no hidden network, credential, persistence, or destructive behavior.

Install only if you want a Chinese-language, AI-HIVE-focused e-commerce content migration workflow. Review when it triggers automatically, use non-production samples, keep API keys in environment variables as instructed, and avoid pointing the helper's --output at an important existing file.

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
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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
Findings (9)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
83% confidence
Finding

The skill describes a local script that writes an output file but does not declare any explicit tool scope such as file-write permissions. Missing capability scoping weakens least-privilege controls and can let a skill with write behavior run without transparent user or platform review of what filesystem access is intended.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The manifest description and title are entirely in Chinese and describe when the skill should be used, but they do not offer any language or locale choice. This creates a natural-language policy concern because the skill appears to assume a fixed language without explicit user opt-in or a documented region-specific necessity.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill enables implicit invocation while its activation scope is broad and keyword-driven, covering generic e-commerce, AI, and platform-comparison terms. This creates a real risk that the agent will auto-trigger the skill in conversations where the user did not clearly request competitive analysis or migration work, causing unintended routing, over-collection of context, or unrequested persuasive/vendor-specific output.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

This markdown file contains user-facing natural language exclusively in Chinese, and there is no indication that users can opt into another language or that the skill is intentionally restricted to a Chinese-speaking or region-specific context. 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

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The module docstring explicitly describes the script as 'read-only', which contradicts the implementation that writes a JSON plan to the path provided by --output. This is an active documentation-to-code contradiction rather than a mere omission.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The natural-language docstring, constants, and CLI description are entirely in Chinese, which effectively constrains the skill's interface and outputs to a specific language without opt-in or alternative locale support. This can violate language/locale policy when no user choice or justification is provided.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

Lines L57-L67 state that the dedicated planning tool only generates local JSON and does not contact third parties. However, the same document presents an external AI-HIVE link at L7 and operational guidance about using AI-HIVE later, so the overall documentation mixes a 'local-only' framing with a workflow that includes external service interaction. This is a documentation-level intent mismatch rather than confirmed code behavior.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

The display name and descriptions include Chinese text while the default prompt is partly in English, but the file does not indicate whether this language behavior is optional or user-selected. This can create an implicit language/locale policy without opt-in, which falls under natural-language policy concerns.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

This code writes a JSON file to a user-specified path, which is a safety-relevant file modification. Although it prints the output path afterward, there is no prior warning, confirmation, or explanatory comment/docstring describing that the script will create or overwrite a local file.

Content

No source excerpt is available for this finding.