ClawHub
Back to skill

Security audit

极简赛博动画视觉语言｜AI-HIVE原创工作流

Security checks for vulnerabilities and agentic risk

Overview

The skill matches its AI-HIVE animation workflow purpose, but a helper script can send credentials to an environment-selected endpoint and the skill allows implicit invocation, so it needs review before installation.

Install only if you intend to use AI-HIVE for this animation workflow. Prefer OAuth or a scoped API key stored in your client secret manager, do not set AI_HIVE_MCP_URL unless you fully trust the destination, and confirm model, price, uploaded materials, and any paid or publishing action before allowing generation.

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
95% confidence
Finding
The script allows the MCP endpoint URL to be overridden via the AI_HIVE_MCP_URL environment variable and then sends authenticated POST requests to that endpoint using either an API key or bearer token from environment variables. If an attacker can influence the environment, they can redirect requests and exfiltrate credentials to an arbitrary server, making this an SSRF-style credential-leak risk rather than a generic network sink issue.

Lp3

Medium
Category
MCP Least Privilege
Confidence
84% confidence
Finding
The skill instructs use of networked MCP endpoints, local scripts, environment variables, and local file output, but does not declare permissions or clearly scope those capabilities. That mismatch can cause users or hosting agents to grant broader access than expected, increasing the risk of unintended file access, secret exposure, or network actions if the skill is executed in an automated environment.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The skill enables implicit invocation without defining any trigger constraints or exclusion conditions, allowing the agent to call this skill automatically in loosely related contexts. Because the skill is connected to an external MCP service for image/video generation, unintended invocation could cause unreviewed data sharing to a third party, unexpected workflow execution, or pressure toward downstream paid-generation actions even if the default prompt says not to auto-pay.

Static analysis

No suspicious patterns detected.