Back to skill

Security audit

AI大模型专家|HappyHorse 视频生成与编辑

Security checks for vulnerabilities and agentic risk

Overview

This skill appears purpose-aligned for AI-HIVE video generation, but it needs review because it can send API credentials and user-selected media through insufficiently constrained network endpoints.

Review this before installing if you will use a real AI-HIVE key or sensitive media. Use only the default AI-HIVE endpoint, avoid setting AI_HIVE_BASE_URL or --base-url unless you fully trust the endpoint, and confirm tasks before running prompts that may incur cost or upload private assets.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (2)

T09 · Insecure Skill Coding Practices

Error
Location
scripts/videogen.py:90
Finding

Bearer API Key Disclosure Through an Unrestricted Base URL

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/videogen.py:277
Finding

Unvalidated Server-Supplied Upload and Download URLs

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding

The skill describes and invokes capabilities equivalent to shell execution, network access, reading environment/config secrets, and file write/download behavior, but it does not declare any tool scope or allowed-tools boundary in the manifest. That creates an authorization ambiguity where a host or reviewer cannot easily determine the minimum required privileges, increasing the risk of overbroad execution, secret exposure, or unintended file/network actions.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The manifest explicitly sets language: zh-CN, which indicates a fixed locale preference. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is clearly justified, and no such user choice or justification is provided here.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The manifest enables implicit invocation while pairing it with a very broad default prompt that can trigger real external actions: submitting media-generation jobs, uploading assets, polling task status, and downloading outputs. Without explicit trigger constraints, confirmation gates, or exclusion conditions, the skill may be invoked in contexts the user did not clearly intend, causing unintended API usage, data transfer, and billing exposure.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The module docstring and user-facing help/instructions are written in Chinese, and the skill does not indicate that language is optional or region-specific. This creates a natural-language locale constraint that may exclude users expecting language choice.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

Natural-language policy checks apply to all file types. The display name, description, and default prompt force a specific language presentation without offering a language/locale choice or documenting that the skill is intentionally limited to Chinese-speaking users.

Content

No source excerpt is available for this finding.