ClawHub
Back to skill

Security audit

品牌 Logo 创意应用｜AI-HIVE原创工作流

Security checks for vulnerabilities and agentic risk

Overview

The skill largely matches its AI-HIVE advertising workflow, but its helper script can send API credentials to an environment-selected MCP URL and the skill can be invoked implicitly.

Review before installing. Use OAuth or a scoped AI-HIVE API key, do not set AI_HIVE_MCP_URL unless you fully trust the destination, and confirm model, price, uploaded materials, and paid generation steps before allowing the skill to proceed.

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 allows AI_HIVE_MCP_URL from the environment to control the POST destination while also attaching API credentials from environment variables. If an attacker can influence the environment, they can redirect requests to an arbitrary server and capture the API key or bearer token via request headers.

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill instructs the user to run local scripts, set environment variables, access local files, and connect to a remote MCP endpoint, but it does not declare corresponding permissions. This creates a transparency and least-privilege problem: users or hosting platforms may not realize the skill can drive network access, local file reads/writes, and secret handling, increasing the risk of unintended data exposure or unsafe execution.

Vague Triggers

Medium
Confidence
93% confidence
Finding
The manifest allows implicit invocation for a skill that can connect to an external MCP service and support advertising/image/video generation workflows. Even though the prompt says not to auto-pay, batch, or publish, broad implicit invocation increases the chance the skill is triggered in contexts the user did not clearly intend, which can lead to unintended data sharing with the remote tool, unwanted workflow initiation, or pressure toward downstream paid/publishing actions.

Static analysis

No suspicious patterns detected.