Skill flagged — suspicious patterns detected

ClawHub Security flagged this skill as suspicious. Review the scan results before using.

图片生成技能 - 支持动态 API 配置和任务记忆,根据 Token 自动获取可用功能,支持文生图和图生图

v1.0.4

GNano Ihogmn 图片生成技能 - 支持动态 API 配置,根据 Token 自动获取可用功能,支持文生图和图生图

0· 92·0 current·0 all-time
byDanielchen@danielchen59
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Suspicious
medium confidence
Purpose & Capability
The name/description (image generation via a token-configured API) align with the included scripts (get_config.py and generate_image.py) which query models and post generation requests. However, pyproject.toml advertises a 'gnano-task' entrypoint mapping to scripts.task_manager that does not exist in the package, and SKILL.md claims WorkBuddy will auto-read/write task state under .workbuddy — but no provided script implements task persistence. This mismatch suggests the package is incomplete or poorly packaged.
Instruction Scope
SKILL.md restricts actions to asking the user for an API token, calling the included scripts, and reading/writing images in the workspace. The Python code follows that scope (reads reference images, encodes them, posts to the configured API, writes generated images). There is no code that reads unrelated system files or environment variables. The inconsistency is that SKILL.md implies automatic task state management in .workbuddy; the code does not implement that, so the documented runtime behavior may not match actual behavior.
Install Mechanism
No install spec is provided (instruction-only install). The project only depends on the widely used 'requests' package (requirements.txt / pyproject). No remote downloads or installers are present in the package.
Credentials
The skill requires a per-task API token supplied by the user (described in SKILL.md). There are no required environment variables or unrelated credentials. This is proportionate to the stated purpose.
Persistence & Privilege
The skill does not request elevated privileges nor set always:true. It reads/writes files in the workspace (reference images and generated outputs), which is expected. Note: pyproject claims a task manager CLI entrypoint that is missing; SKILL.md states task state is stored under .workbuddy/gnano-tasks/, but that persistence is not implemented in the provided scripts, so the actual persistence behavior is unclear.
What to consider before installing
This skill appears to implement token-based image generation and the included scripts largely match that purpose, but there are a few worrying signs you should consider before installing or providing any real API token: - Unknown API endpoint: The default API URL is https://gnano.ihogmn.top — this is not an established public provider. Only supply a token if you trust that endpoint. - Packaging inconsistencies: pyproject.toml advertises a 'gnano-task' entrypoint (scripts.task_manager) that isn't included, and SKILL.md asserts automatic task state storage under .workbuddy; the provided scripts don't implement that. This suggests the package may be incomplete or poorly maintained. - Code behavior: The scripts read workspace files (reference images) and write output images; they do not access other system files or environment variables. Still, review the code locally if possible (or run in a sandbox) to confirm there is no hidden behavior. - Practical advice: If you try it, use a throwaway/test API token, run the scripts in an isolated workspace, and monitor outbound network traffic to confirm the token is sent only to the intended API host. If you need persistent task memory, verify how that is implemented (the package currently lacks a task_manager implementation). Given these points, proceed cautiously; the issues look like sloppy packaging rather than explicit malicious intent, but the unknown external API and missing files raise enough uncertainty to classify the skill as 'suspicious.'

Like a lobster shell, security has layers — review code before you run it.

latestvk973896wne4mq6f1vvq5qhws7h83eqr3

License

MIT-0
Free to use, modify, and redistribute. No attribution required.

Comments