Back to skill

Security audit

快手电商视频生成与编辑

Security checks for vulnerabilities and agentic risk

Overview

The skill mostly matches its video-generation purpose, but it can send a stored AI Hive API key to an arbitrary configured API host, which is a real credential-risk concern.

Review this skill before installing if you will use a real AI Hive API key. Use only the documented AI Hive base URL, avoid setting --base-url or AI_HIVE_BASE_URL from untrusted instructions, and treat uploaded media as being sent to the configured service. Prefer an isolated Python environment and pin dependencies before operational use.

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:93
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:277
Finding

Unvalidated Server-Supplied Media Transfer URLs

Content
View full analysis
Remediation
View remediation

T08 · Insecure Dependencies

Note
Location
SKILL.md:69
Finding

Unpinned Runtime Dependency Installation

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
Findings (10)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

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

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
86% confidence
Finding

The skill includes executable setup and task commands that imply shell, network, and file access, but it does not declare any tool scope or permission boundaries. This can cause an agent platform to invoke the skill without clear least-privilege constraints, increasing the risk of unintended command execution, package installation, network access, or file operations.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The description uses very broad 'use this skill for' language covering many ecommerce and video scenarios without clear invocation limits. Over-broad triggers can cause accidental or excessive activation, which matters more here because the skill also contains executable commands and media-processing workflows that may consume resources or perform unintended actions.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The skill content is written to operate in Chinese and is targeted at Chinese-language Kuaishou ecommerce workflows, without indicating language negotiation or user opt-in. This can override user language expectations, leading to confusing outputs, mistaken approvals, or misinterpretation of operational instructions in a workflow that may involve publishing or executing tasks.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The file is presented as a Kuaishou e-commerce video generation/editing skill, but it embeds a much broader generic AI client with chat, image generation, model listing, user-info retrieval, and raw upload flows. This creates a capability/scope mismatch that can bypass policy expectations, increase attack surface, and enable operators or downstream agents to invoke functions unrelated to the declared purpose.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The module docstring presents the skill entirely in Chinese and frames it as a general-purpose tool ("通用 AI 能力调用工具"), but it does not indicate that Chinese is optional or that the tool is region-specific. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

Exposing user/account information retrieval is unrelated to e-commerce video generation and gives the skill visibility into account details and wallet/balance data. In an agent setting, this broadens data access beyond user expectations and can facilitate unnecessary sensitive-data disclosure or reconnaissance.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The generic text-chat capability is outside the stated purpose of video generation/editing and effectively turns the skill into a broader LLM interface. That increases the chance of policy bypass, prompt misuse, and unintended data transmission to external services under the cover of a narrowly described media tool.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

Standalone image generation exceeds the declared video-generation/editing scope and introduces additional model invocation pathways not implied by the skill metadata. This mismatch makes the skill more dangerous in an agent ecosystem because it can be used for unrelated content generation while appearing to be a specialized video tool.

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 configuration content. There is no indication that the skill is region-specific or that other language options are supported, so this appears to violate the language/locale policy for natural-language content.

Content

No source excerpt is available for this finding.