Back to skill

Security audit

AI大模型专家|抖音电商 电商视频生成与编辑

Security checks for vulnerabilities and agentic risk

Overview

The skill mostly does what it claims, but it handles API credentials and paid external video jobs with too little boundary control.

Review before installing. Keep the API base URL at the documented AI-HIVE endpoint, use a limited/rotatable API key, avoid implicit or automatic runs unless your agent asks for confirmation before uploads and job submission, and install dependencies in an isolated environment.

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 (2)

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/videogen.py:92
Finding

Bearer API Key Can Be Transmitted to an Arbitrary Configured Server

Content
View full analysis
Remediation
View remediation

T08 · Insecure Dependencies

Note
Location
SKILL.md:257
Finding

Unpinned Runtime Dependency Installation

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
  • 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 (7)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding

The skill documents capabilities that involve network access, shell execution, filesystem reads/writes, and environment/config handling, but it does not declare any explicit tool scope or permission boundaries. In an agent environment, this can lead to overbroad authority: the skill may access local files, stored API keys, or remote endpoints beyond what the user expects, increasing the blast radius if the skill is misused or its instructions are manipulated.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The metadata sets language: zh-CN, and the document content is written to enforce a Chinese-language experience without indicating that users may choose another language. The policy allows locale constraints only when they are optional or clearly justified as region-specific; this file does not provide that opt-in framing.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill enables implicit invocation with no activation constraints, so the platform may auto-select and run a capability that can upload user-provided media, submit external jobs, poll status, and download outputs without a clear, explicit user opt-in. In a skill that triggers real external workflows and potential cost-incurring actions through AI-HIVE, this increases the risk of unintended data disclosure, surprise charges, and execution of actions the user did not specifically authorize.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The file starts as a broad '通用 AI 能力调用工具' and includes generic chat, image generation, model listing, upload, and task APIs, while the packaged skill is declared for Douyin e-commerce video generation/editing. This scope mismatch weakens least-privilege expectations: a caller selecting this skill could access unrelated AI capabilities not implied by the manifest, increasing the chance of misuse, policy bypass, or unexpected data handling.

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 strings and documentation entirely in Chinese, including the module docstring and CLI guidance. There is no indication that the user can choose another language or that the locale restriction is required for a region-specific compliance reason, which conflicts with the language/locale policy criteria.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The user-facing name and descriptions are entirely in Chinese, which may impose a language choice on users without offering opt-in or documenting that the skill is intended only for a Chinese-speaking or region-specific audience. This can violate language/locale policy where user choice or explicit justification is required.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The top-level docstring states this is a '通用 AI 能力调用工具' that wraps text chat, image generation, video generation, model query, media upload, and task polling. That actively conflicts with the skill packaging at the bottom of the file, which brands the artifact as a specialized 抖音电商 video generation/editing skill.

Content

No source excerpt is available for this finding.