Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Baoyu Image Gen
v1.0.0AI image generation with OpenAI, Google, DashScope and Replicate APIs. Supports text-to-image, reference images, aspect ratios. Sequential by default; parall...
⭐ 0· 1.6k·70 current·70 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
medium confidencePurpose & Capability
Name/description match code and instructions: the skill implements text-to-image and reference-image flows for Google, OpenAI, DashScope, and Replicate. Environment variables and behaviors requested (API keys, model overrides, reading prompt/ref files, saving EXTEND.md preferences) are consistent with an image-generation CLI.
Instruction Scope
Runtime instructions and code read .baoyu-skills EXTEND.md (project or user) and may create/update it (expected for saving preferences). The code also loads env files from ~/.baoyu-skills/.env and <cwd>/.baoyu-skills/.env which will set provider API keys — this is proportionate but important to understand. The notable risk: google.postGoogleJsonViaCurl uses child_process.execSync to run curl with the API key embedded in the command string (x-goog-api-key header). That exposes the API key to observers of process command lines (ps) and is a security-practice concern.
Install Mechanism
No install spec (instruction-only with included scripts). That is low-risk from an install perspective — nothing is downloaded at install time. The code expects to be run via npx/bun but has no external install hooks.
Credentials
SKILL.md lists provider API keys and base URL overrides (OPENAI_API_KEY, GOOGLE_API_KEY/GEMINI_API_KEY, DASHSCOPE_API_KEY, REPLICATE_API_TOKEN, etc.). These are expected for a multi-provider image tool. Registry metadata had 'required env vars: none' but the skill clearly uses provider credentials; this is a metadata mismatch (minor). The skill also loads .env files from project and home — convenient but means secrets can be loaded from those files.
Persistence & Privilege
always:false and user-invocable. The skill writes its own EXTEND.md into .baoyu-skills in project or user home to store preferences — this is reasonable for a preferences feature and does not change other skills or system-wide settings.
Assessment
This skill is consistent with its stated purpose (multi-provider image generation) and will need the provider API keys to work. Before installing, consider: 1) Keep API keys out of project repos — prefer setting them in a secure environment or a user-scoped .baoyu-skills/.env file with restrictive file permissions. 2) The code sometimes uses curl via execSync and embeds the Google API key in the command line when an HTTP proxy is detected; on some systems that can expose the key to other local users via process listings. If this concerns you, review/modify scripts to avoid placing secrets on the command line (e.g., use a library HTTP client or pass headers via stdin or environment). 3) The skill will read prompt/reference files you point it to and will write EXTEND.md under .baoyu-skills — do not run it in repositories with sensitive files you didn't intend to expose. 4) Metadata omitted required env vars in the registry; verify you provide only needed credentials. If you need higher assurance, review the included source files locally and run in a trusted environment.Like a lobster shell, security has layers — review code before you run it.
latestvk9729g5nz0xhdycm68v85f48wn82dr7v
License
MIT-0
Free to use, modify, and redistribute. No attribution required.