Back to skill

Security audit

TikTok Shop 爆款带货视频生成

Security checks for vulnerabilities and agentic risk

Overview

The skill is a plausible AI Hive video generator, but it needs review because it handles API keys, local media uploads, and downloads with under-scoped URL and file-write protections.

Install only if you trust AI Hive and the publisher, use a dedicated API key with limited balance or permissions if possible, avoid setting AI_HIVE_BASE_URL or --base-url to non-official hosts, run it in a constrained environment for sensitive media, and choose an output directory where accidental overwrites would not be damaging.

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 (4)

T09 · Insecure Skill Coding Practices

Error
Location
scripts/videogen.py:91
Finding

API Key Disclosure Through an Unrestricted Base URL

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Error
Location
scripts/videogen.py:278
Finding

Unvalidated Server-Controlled Upload and Download URLs

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Error
Location
scripts/videogen.py:394
Finding

Path Traversal Through Server-Controlled Download Filenames

Content
View full analysis
Remediation
View remediation

T08 · Insecure Dependencies

Warning
Location
SKILL.md:87
Finding

Unpinned Runtime Dependency Installation

Content
View full analysis
``` The script repeats the unpinned installation instruction: ```python try: import requests except ImportError: print("Missing dependency: requests. Run pip3 install requests", file=sys.stderr) sys.exit(1) ``` ### Technical Analysis The project instructs users to install `requests` without a fixed version, dependency lock file, or package hash. Installation therefore resolves the package and all transitive dependencies according to mutable package-index state at installation time. Although `requests` is a legitimate package and no malicious dependency is embedded in this project, the installation procedure is not reproducible. Future releases, compromised distribution infrastructure, an unsafe package-index configuration, or dependency-resolution changes could introduce unreviewed code. Python packages may execute code during installation and are imported into the skill process, giving a compromised dependency the same local privileges as the invoking user. ### Attack Path 1. A user follows the documented command: ```bash pip3 install requests ``` 2. `pip` contacts its configured package index and resolves the current available package and dependency versions. 3. No project-controlled version constraint or cryptographic hash verifies the expected artifacts. 4. A compromised or unexpectedly changed package is installed. 5. The package executes during installation or when `videogen.py` imports `requests`. 6. The dependency gains access to the process environment, local files available to the user, API credentials, and media ...[truncated 554 chars]
Remediation
View remediation
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 (8)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

This markdown file uses Chinese-language release notes throughout the substantive content, but does not indicate that the skill is region-specific or provide an opt-in language/locale choice. Under the policy rule, forcing a specific language without user opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding

The skill invokes a local Python script with shell commands, supports reading local media inputs, writing outputs, and likely making network requests to external video-generation endpoints, but it does not declare any explicit tool scope or permissions. This creates a trust and containment gap: an agent may grant broader file, shell, environment, or network access than users expect, increasing the risk of unintended data exposure or command execution through this skill.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The module docstring and implemented CLI expose generic AI Hive capabilities including text chat, image generation, model listing, user info retrieval, media upload, and task polling, not just TikTok Shop sales video creation/editing. While some helper operations are expected for video generation, full chat and standalone image-generation workflows materially broaden behavior beyond the manifest’s stated video-focused scope.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill implements a generic chat/text API and exposes it via the chat subcommand, including multimodal image input. A TikTok Shop viral sales video generation skill may reasonably use prompts internally, but offering a general-purpose chat interface is a separate capability not justified by the manifest’s video-creation scope.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The code exposes a full image-generation workflow independent of video generation. Although reference images can be relevant to video creation, a separate image generator is not clearly justified by a skill whose manifest is specifically about creating and editing TikTok Shop sales videos.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
85% confidence
Finding

The embedded SKILL_CONFIG hard-codes the skill as a 'TikTok Shop 爆款带货视频生成' tool for overseas social commerce and TikTok Shop marketing use. This constrains the skill to a specific market/platform context in natural-language metadata without offering the user a choice of locale/market framing or documenting why that policy is required.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The example API key placeholder uses Chinese text ('请替换为你的APIKey'), which imposes a specific language in user-facing natural language content. This can violate language/locale policy when no user opt-in or documented regional justification is provided.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The code provides a user-info endpoint and CLI command that retrieves account information and wallet balance. That capability is not an obvious requirement for creating or editing TikTok Shop UGC sales videos, and the manifest does not mention account inspection or billing visibility as part of the skill’s scope.

Content

No source excerpt is available for this finding.