Back to skill

Security audit

抖音爆款短视频生成与编辑

Security checks for vulnerabilities and agentic risk

Overview

The skill is coherent for AI Hive Douyin video generation, but its downloader can write outside the chosen output folder if task metadata from the API is crafted maliciously.

Review before installing if you will use custom or untrusted AI Hive base URLs, because crafted task metadata could cause downloaded output files to be written outside the selected output directory. Use a virtual environment, avoid elevated privileges, keep the API key private, and only upload media you are comfortable sending to AI Hive.

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

Error
Location
scripts/videogen.py:399
Finding

Untrusted API Fields Permit Download Path Traversal

Content
View full analysis
Remediation
View remediation

T08 · Insecure Dependencies

Warning
Location
SKILL.md:79
Finding

Unpinned Third-Party Dependency Installation

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (9)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown file contains user-facing natural-language content exclusively in Chinese across the substantive changelog entries. Under the policy, forcing a specific language without user opt-in or justification is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding

The skill exposes shell, network, file read/write, and environment-dependent execution examples but does not declare any explicit tool scope or permissions boundaries. That makes it easier for an agent runtime to invoke the skill with broader-than-necessary capabilities, increasing the chance of unintended command execution, filesystem access, dependency installation, or network use if the skill is triggered in the wrong context.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The description uses broad 'Use this skill for ...' language across many marketing and video-production scenarios without tight trigger conditions. In agent environments, this can cause over-invocation or invocation in ambiguous contexts, which is risky here because the skill includes executable shell commands, package installation, file operations, and networked generation workflows.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The manifest describes a skill focused on generating and editing Douyin-oriented videos, including text-to-video, image-to-video, reference video, remix, and extension workflows. However, the same file implements a generic AI Hive chat/text client and a full chat command for multimodal text interaction, which is outside the stated video-editing purpose.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

Beyond video generation, the code includes an image command for general image generation plus user-info and models commands for account/model introspection. Those are broader AI-platform utility functions rather than capabilities clearly implied by a Douyin viral-video generation/editing skill.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

This code embeds natural-language strings and metadata that position the skill specifically for '抖音爆款短视频' generation and presents the CLI description/help text in Chinese only. The policy requires flagging language or locale constraints when they are imposed without explicit user choice or documented justification as a region-specific compliance tool.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill instructions and examples are predominantly in Chinese, and there is no natural-language indication that users may choose another language or locale. This can violate language/locale policy when a skill effectively forces one language without user opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

The placeholder value 请替换为你的APIKey forces a specific language in user-facing configuration text. There is no indication that the skill is region-specific or that alternative locales are supported, so this appears to violate the language/locale policy for natural-language content.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The manifest describes content-generation and editing workflows, but this file also includes an interactive onboarding routine that launches a browser, walks the user through account login/API key creation, and writes credentials locally. That is an account-bootstrap capability, not a direct video-generation function.

Content

No source excerpt is available for this finding.