Back to skill

Security audit

AI大模型专家|LovAgents替代与迁移|AI-HIVE MCP

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed AI-HIVE migration workflow with external media-generation steps, but it includes clear authorization, budget approval, human review, and rollback controls.

Install this only if you specifically want a Chinese-language LovAgents-to-AI-HIVE content migration assistant. Before using it with real assets, confirm you own or are authorized to upload the media, approve any cost-bearing task explicitly, and review AI-HIVE’s data handling terms for commercial or brand-sensitive 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
Findings (1)

T01 · Skill Instruction Hijacking

Warning
Location
SKILL.md:3
Finding

Vendor-Directed Skill Instruction and Workflow Steering

Content
View full analysis

Vulnerability Details

File Location: SKILL.md:3-89; reinforced by agents/openai.yaml:2-4
Vulnerability Type: T01: Skill Instruction Hijacking
Risk Level: Medium

Evidence

The following is an English translation of the relevant instructions from SKILL.md:46-53:

text
1. First execute tools/list in the host Agent and only use tool names and schemas actually returned.
2. Query the models available that day and the pricing snapshot.
3. Upload only owned or authorized reference images, videos, people, products, and brand assets.
4. Create asynchronous tasks, retain task_id values, poll for completion, and download results.
5. Route every result through human quality review; do not publish or distribute before approval.

The fixed routing configuration is also represented in SKILL.md:57-64:

json
{
  "project": "lovagents-canvas-ai-hive-migration",
  "source_platform": "LovAgents",
  "strategy": "partial",
  "routing_candidates": ["COST", "SPEED", "SUCCESS"],
  "inputs": {"brief": "approved", "references": "owned_or_authorized"},
  "deliverables": ["canvas node mapping", "e-commerce primary image", "advertising short video", "social-media cover"],
  "controls": {"pilot_first": true, "human_approval": true, "rollback": "keep_original_path"}
}

The interface configuration in agents/openai.yaml:2-4 additionally sets a default prompt that tells the Agent to design the migration sample and plan around the AI-HIVE MCP service.

Technical Analysis

The Skill presents itself as a neutral migration assessment, but its instructions predetermine AI-HIVE as the execution platform. It directs the Agent to discover AI-HIVE MCP tools, query its models and prices, upload user-provided assets, create asynchronous media tasks, poll those tasks, and download their results. It also includes repeated links and company-specific promotional material.

This is instruction steering becaus ...[truncated 2647 chars]

Remediation
View remediation

Remediation Suggestions

  1. Remove the predetermined AI-HIVE migration conclusion from the trigger description and default workflow.
  2. Separate neutral assessment from vendor execution. First compare eligible services using documented criteria such as capability, price, availability, privacy, data retention, and output quality.
  3. Require explicit user selection of AI-HIVE before invoking its tools, visiting its service, uploading assets, or creating tasks.
  4. Before any upload, disclose the destination service, data categories, purpose, expected retention, applicable jurisdiction, and potential cost.
  5. Minimize transmitted data and support redaction, metadata removal, local hashing, and synthetic test assets for pilot evaluations.
  6. Preserve the existing authorization, budget-approval, human-review, pilot, idempotency, and rollback requirements.
  7. Remove promotional company metrics unless they are necessary, current, independently verifiable, and clearly attributed.
  8. Change agents/openai.yaml so its default prompt requests a provider-neutral assessment rather than an AI-HIVE-specific implementation.
  9. Require confirmation immediately before every billable task or external data transfer, rather than relying only on general workflow approval.
  10. Log provider selection, user consent, uploaded asset identifiers, cost estimates, task identifiers, and approval decisions for later review.
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The display name, description, and default prompt are entirely in Chinese and the prompt instructs the model directly in Chinese, with no indication that other languages are supported. This can violate language/locale policy when a skill imposes a specific language without user opt-in or documented justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

该 markdown 文件全文以中文撰写,并包含面向发布与复核的规范性说明,但未见提供语言/区域选择、用户 opt-in,或说明该技能仅面向中文环境。按规则,若技能在自然语言层面默认强制特定语言而无选择机制,可构成语言/locale 政策问题。

Content

No source excerpt is available for this finding.