T09 · Insecure Skill Coding Practices
- Location
scripts/videogen.py:92- Finding
Bearer API Key Can Be Transmitted to an Arbitrary Configured Server
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
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.
scripts/videogen.py:92Bearer API Key Can Be Transmitted to an Arbitrary Configured Server
SKILL.md:257Unpinned Runtime Dependency Installation
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.
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.
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.
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.
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.
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.
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.