T08 · Insecure Dependencies
- Location
SKILL.md:72- Finding
Unpinned Runtime Dependency Installation
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
The skill appears to generate marketing images as advertised, but it needs review because a custom API endpoint can receive the user's bearer API key without clear safeguards.
Review this before installing if you will use a real AI Hive API key. Use only the official AI Hive endpoint, avoid setting AI_HIVE_BASE_URL or --base-url unless you control the server, install dependencies from a trusted pinned environment, and remember that reference images are uploaded to the service and generated files are downloaded to ~/Downloads/AiHive by default.
SKILL.md:72Unpinned Runtime Dependency Installation
scripts/imagegen.py:73Bearer Credential Disclosure Through Unrestricted Base URL Override
The declared purpose is narrow marketing-image generation, but the underlying implementation reportedly supports unrelated capabilities such as chat, video generation, user/account queries, file download, browser opening, and local config writes. That mismatch is dangerous because users and policy systems may authorize the skill under false assumptions, enabling privilege expansion and data access beyond the advertised use case.
The changelog content is written entirely in Chinese for multiple feature descriptions and platform notes, with no indication that language selection is optional or that the skill is intended only for a Chinese-speaking or region-specific audience. Under the policy rule for natural-language violations, this can be a locale/language constraint that is not clearly documented as opt-in or justified.
The skill exposes shell, network, file read/write, and environment capabilities through documented commands but declares no explicit tool scope or permissions. This weakens least-privilege guarantees and can let a seemingly simple image-generation skill perform broader actions than users or orchestrators expect if the backing scripts are modified or abused.
The manifest description lists many generic triggers such as '品牌Campaign', '活动海报', '社媒内容', and '多渠道营销资产' without clear boundaries or negative examples. This makes activation scope ambiguous and could cause unintended invocation for ordinary marketing-related requests.
The natural-language instructions are entirely written in Chinese and direct the workflow in that locale, but the skill does not state that language is optional or region-specific. This can violate language/locale policy where users should be given a choice unless the locale restriction is explicitly justified.
The top-level docstring says the file is a '通用 AI 能力调用工具' wrapping text chat, image generation, video generation, model querying, media upload, and task polling. But the actual entry point executed by this skill is the specialized skill_main flow that fixes the model to GPT Image 2 and presents itself as a dedicated marketing-image skill. This documentation therefore describes a materially different intent than the skill file actually serves.
The module docstring and all user-facing CLI messages are written in Chinese, which effectively fixes the skill's interaction language without offering any user opt-in or alternative locale. Under the stated policy, forcing a specific language is a natural-language policy violation unless the locale constraint is explicitly justified or optional.
The manifest describes a focused skill for generating a set of GPT Image 2 marketing images. However, the shipped skill interface also includes separate task and upload subcommands, letting users query arbitrary generation tasks and upload media independently of marketing image creation. Those capabilities go beyond the narrow generation purpose stated in the manifest.
The sample API key value includes Chinese text ('请替换为你的APIKey'), which imposes a specific language in user-facing configuration content. This can violate language/locale policy when no alternative language choice or justification is provided.