Back to skill

Security audit

AI开箱视频生成器|AI-HIVE

Security checks for vulnerabilities and agentic risk

Overview

This skill mostly matches its AI-HIVE video-generation purpose, but it handles API credentials and network downloads with weaker scoping than users should accept without review.

Install only if you trust the AI-HIVE endpoint and understand that the skill can store an API key, upload selected media, submit potentially billable generation jobs, and download generated files. Avoid custom base URLs, keep AI_HIVE_BASE_URL unset unless you control the endpoint, and review prompts and media paths before generation.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
Findings (3)

T09 · Insecure Skill Coding Practices

Error
Location
scripts/videogen.py:94
Finding

API Credential Disclosure Through an Unrestricted Base URL

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/videogen.py:280
Finding

Unvalidated Server-Supplied Upload and Download URLs

Content
View full analysis
Remediation
View remediation

T08 · Insecure Dependencies

Note
Location
scripts/videogen.py:8
Finding

Unpinned Third-Party Dependency Installation

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Findings (12)

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

A second description-behavior mismatch reinforces that the skill is presented as a specialized unboxing-video generator while the actual material points to generic ffmpeg-style processing rather than the claimed business logic. In security terms, deceptive capability descriptions weaken operator judgment, can bypass expected review gates, and may cause downstream systems to grant trust or permissions based on functions the skill does not truly provide.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

A second description-behavior mismatch reinforces that the skill is presented as a specialized unboxing-video generator while the actual material points to generic ffmpeg-style processing rather than the claimed business logic. In security terms, deceptive capability descriptions weaken operator judgment, can bypass expected review gates, and may cause downstream systems to grant trust or permissions based on functions the skill does not truly provide.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding

The skill includes executable workflows and sample commands that rely on environment variables, filesystem access, network access, and shell execution, but it does not declare any explicit tool scope or permissions boundary. In an agent setting, this creates an overbroad execution surface where the runtime may permit sensitive operations without clear least-privilege constraints, increasing the chance of unintended API use, data exfiltration, or destructive local actions.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
85% confidence
Finding

The skill description, usage instructions, and expected outputs are consistently presented in Chinese, which can amount to a language-policy constraint if the skill effectively forces that language by default. The file does not explicitly offer a language choice or explain that the skill is intentionally limited to a Chinese-speaking or region-specific context.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger phrases are broad and include common commercial terms like '新品发布' and '商品展示', which can cause the skill to activate in contexts far beyond its intended narrow use case. Over-broad triggering is risky because an agent may invoke this skill in unrelated conversations, exposing users to unnecessary file/network/tool workflows or causing the model to follow an ill-suited process on sensitive marketing, brand, or media tasks.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The default prompt hard-codes a Chinese-language response style ('production-ready Chinese workflow') without checking the user's language preference. This can override user intent or downstream agent expectations, creating prompt steering and usability issues; while not a direct code-execution risk, it is a real prompt-level policy weakness because it imposes behavior the user did not explicitly request.

Content

No source excerpt is available for this finding.

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · scripts/edit_video.py (reported line 20)May include surrounding context.

python
def run(args: list[str]) -> None:
    print(" ".join(args))
    subprocess.run(args, check=True)


def main() -> None:

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest describes a narrowly scoped skill for AI unboxing/e-commerce video generation, packaging order design, and related video workflows. However, the file implements a generic AI Hive client with chat, image, models, and user-info commands, enabling broad text chat and image generation operations beyond the stated unboxing-video purpose.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The top-level docstring explicitly says this is a '通用 AI 能力调用工具' and lists broad capabilities including text chat, image generation, video generation, model queries, media upload, and task polling. That directly conflicts with the surrounding skill identity and manifest, which present a specialized AI unboxing video generator rather than a general-purpose multimodal API client.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This code file contains user-facing natural language entirely in Chinese, including the module description and CLI guidance, while presenting itself as a general-purpose tool. The skill does not indicate that Chinese is optional or that other languages/locales are supported, which can violate language/locale choice policy for broadly scoped skills.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill-specific parser and dispatcher allow users to select multiple generation modes and pass arbitrary media inputs and free-form model parameters, enabling broader model use than the narrow unboxing-video use case suggests. In an agent-skill context, this capability expansion weakens least-privilege boundaries and can let downstream users repurpose the skill for unrelated or policy-sensitive content generation using the same trusted integration.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

This code embeds Chinese-language product/skill names and aliases in the docstring, argument parser description, and output metadata. Because the file provides no language choice, opt-in, or documented region-specific justification, it presents a natural-language locale constraint that may violate language/locale policy.

Content

No source excerpt is available for this finding.