Security audit
Security checks for vulnerabilities and agentic risk
The skill mainly matches its product-image purpose, but it can send the user's AI Hive bearer API key to any configured API base URL, including unsafe or non-AI-Hive endpoints.
Install only if you trust this AI Hive workflow and understand it stores an API key locally and uploads selected reference media. Keep the default HTTPS AI Hive endpoint, do not set `--base-url`, `AI_HIVE_BASE_URL`, or config `base_url` to an unknown or HTTP host, and consider installing dependencies in a virtual environment with pinned versions.
scripts/imagegen.py:91Bearer API key can be transmitted to an arbitrary or plaintext endpoint
SKILL.md:72Runtime dependency installation is not version- or integrity-pinned
The skill invokes shell commands, installs packages, performs networked image-generation tasks, and reads/writes files, but it does not declare any explicit tool restrictions or permissions. That creates unnecessary ambiguity about what runtime capabilities the skill is allowed to use, increasing the risk of over-privileged execution or accidental misuse if an agent auto-enables broad tools for this skill.
The description lists many generic use cases such as product images, Amazon Listing, Shopify product images, SKU batch work, and new-product visuals, which makes activation scope broad and potentially ambiguous. It does not provide explicit trigger phrases, exclusions, or context limits to distinguish when this skill should activate versus other image-generation or e-commerce skills.
The skill content and operational instructions are presented in Chinese, while the description also mixes Chinese and English use cases without stating that language is optional or user-selectable. This can violate language/locale policy when a skill implicitly enforces a specific language without opt-in.
The top-level docstring says the file wraps text chat, image generation, video generation, model queries, media upload, and task polling as a generic AI Hive OpenAPI tool, and the general parser repeats that framing. This actively conflicts with the embedded skill configuration and manifest, which present the file as a dedicated Nano Banana Pro product-image skill.
The module docstring and user-facing CLI text are written in Chinese, and later prompts/errors also assume Chinese throughout the interaction. This imposes a specific language/locale on users without offering any language choice or documenting a justified region-specific constraint.
The manifest describes a focused skill for generating brand-consistent product images via Nano Banana Pro, but this wrapper exposes additional user-facing commands to query arbitrary generation tasks and upload files independently of image generation. Those operations are broader than the claimed 'product image generation' purpose and make the skill act as a more general AI Hive media/task utility.
This markdown file contains user-facing natural-language content exclusively in Chinese across the substantive entries. Under the policy rule for language or locale constraints, forcing a specific language without opt-in or justification can be a policy issue.
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. The file does not offer an alternative locale or indicate that the language choice is intentional or region-specific.
No suspicious patterns detected.