ClawHub
Back to skill

Security audit

Seedance 2.0 提示词专家｜AI-HIVE

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed AI-HIVE video prompt and generation helper, with expected API use and local downloads but no evidence of hidden or destructive behavior.

Install only if you intend to use AI-HIVE with your own API key. Review prompts, routing, price snapshots, and authorized media before submitting generation jobs, and use --no-download or --output-dir if you do not want generated files saved under ~/Downloads/AiHive.

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding
The skill embeds executable code paths and operational guidance for environment variables, filesystem access, shell execution, and network calls, yet it declares no permissions or trust boundaries. This creates a capability-transparency gap: a user or hosting agent may invoke the skill without understanding that it can submit external API requests, write files, or interact with local tooling such as ffmpeg, increasing the risk of unintended data exposure, unexpected charges, or unsafe execution.

Description-Behavior Mismatch

Medium
Confidence
95% confidence
Finding
The file implements a broad AI Hive client with chat, image generation, model enumeration, user-info retrieval, and generic media upload, which materially exceeds the declared Seedance 2.0 prompt-expert/video-generation scope. In a skill environment, this scope expansion increases attack surface and enables unintended data access or side effects that users would not reasonably expect from the manifest.

Context-Inappropriate Capability

Medium
Confidence
93% confidence
Finding
The skill includes a user-info endpoint that can retrieve account details and wallet balance despite this being unnecessary for prompt-authoring/video-generation. Exposing account metadata in an unrelated skill increases privacy risk and can leak sensitive operational or billing information to callers or logs.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
Successful generation results are automatically downloaded and written to a default directory on the user's filesystem unless --no-download is specified. In a skill context, implicit file writes can surprise users, consume disk space, and persist untrusted remote content locally without an explicit confirmation step.

Static analysis

No suspicious patterns detected.