ClawHub
Back to skill

Security audit

电商产品视觉全案生成｜AI-HIVE原创工作流

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent AI-HIVE advertising workflow, but it handles credentials through a helper that can send them to an overrideable endpoint and enables broad implicit invocation.

Install only if you intend to use AI-HIVE for ecommerce advertising generation. Prefer OAuth through the client, avoid setting AI_HIVE_ACCESS_TOKEN manually, do not set AI_HIVE_MCP_URL unless you fully trust the destination, and review every model, price, upload, paid generation, bulk action, send, or public publish step before approving it.

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
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

Tainted flow: 'request' from os.environ.get (line 67, credential/environment) → urllib.request.urlopen (network output)

Critical
Category
Data Flow
Content
method="POST",
    )
    try:
        with urllib.request.urlopen(request, timeout=60) as response:
            result = parse_payload(response.read(), response.headers.get("content-type", ""))
            return result, response.headers.get("mcp-session-id") or session_id
    except urllib.error.HTTPError as error:
Confidence
89% confidence
Finding
The script posts credentials from environment variables to a remote MCP endpoint whose URL is overrideable via AI_HIVE_MCP_URL. That means a user or wrapper process can redirect requests to an arbitrary host and cause the helper to transmit API keys or bearer tokens to an unintended server, creating a credential exfiltration risk.

Lp3

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding
The skill instructs the user/agent to use environment variables, read and write local files, and access a remote MCP endpoint, but it does not declare any permissions for those capabilities. This creates a permission-model mismatch: a reviewer or runtime may treat the skill as lower risk than it really is, while the workflow can still cause network egress, local file creation, and potential secret handling during execution.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The skill enables implicit invocation without defining narrow trigger conditions, so it may activate in response to broad advertising or ecommerce-related prompts without the user intentionally selecting it. Because this skill is connected to a remote MCP service for image, video, and marketing generation, unintended activation expands the chance of unreviewed external data sharing or tool use beyond the user's expectations.

Static analysis

No suspicious patterns detected.