T09 · Insecure Skill Coding Practices
- Location
scripts/videogen.py:93- Finding
API Credential Disclosure Through an Unrestricted Base URL
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
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.
scripts/videogen.py:93API Credential Disclosure Through an Unrestricted Base URL
scripts/videogen.py:277Unvalidated Server-Supplied Media Transfer URLs
SKILL.md:69Unpinned Runtime Dependency Installation
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.