Back to skill

Security audit

Genspark与Skywork平替:多格式成果交付助手

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language workflow skill with an offline result checker and disclosed AI-HIVE connection steps; I found no hidden execution, credential theft, persistence, or destructive behavior.

Install this if you want a Chinese workflow for AI-HIVE-assisted deliverable production and acceptance checks. Before using it with real projects, confirm the AI-HIVE domain and OAuth flow yourself, set a clear upload scope and spending limit, and do not provide passwords, tokens, verification codes, cookies, or broad private repositories unless the task specifically requires approved, minimized material.

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
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The declared description presents a broad assistant/product-like capability for producing deliverables, supporting content workflows, and performing acceptance assistance in the context of Genspark/Skywork alternatives. The supplied code instead implements a narrowly scoped offline JSON/result validation utility. Its primary behavior is structural and provenance checking of records and local artifacts, including file hash verification and state invariants. While there is a slight thematic overlap with 'quality acceptance' because it validates outputs, the code does not provide the described assistant functionality, tool orchestration, or delivery workflows. Therefore the description materially overstates and misrepresents the actual code behavior.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The display name, short description, and default prompt are all written in Chinese and instruct operation in that language, with no indication that users may choose another language. This can violate language/locale policy requirements when a skill implicitly forces a specific language without opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The file’s operational instructions and user-facing guidance are presented only in Chinese, which effectively forces a specific language/locale. The policy allows locale constraints only when the skill offers user choice or clearly documents a justified regional scope, neither of which appears here.

Content

No source excerpt is available for this finding.