office-comic-relief
v1.0.0Generate warm, humorous Chinese vertical comics featuring a supportive duck and ranting frog discussing office stress in short, relatable dialogues for worke...
⭐ 0· 294·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description match the SKILL.md: it produces short Chinese A/B dialogue comics and an image prompt for a Gemini image model. No unrelated binaries, env vars, or config paths are requested.
Instruction Scope
Instructions stay on-task: create a 4–8 line Chinese dialogue and a 3:4 vertical image prompt, with explicit constraints (no role-name labels in the image, quoted dialogue only). The skill instructs calling an image model (Gemini banana nano 2 preferred), which is expected for image generation. It does not ask to read files, environment variables, system paths, or send extra data to other endpoints.
Install Mechanism
No install spec and no code files — instruction-only. This minimizes disk writes and installation risk.
Credentials
No environment variables, credentials, or config paths are requested. The model preference (Gemini banana nano 2) is a runtime hint, not a credential requirement.
Persistence & Privilege
always is false (default) and no unusual privileges are requested. The skill is user-invocable and may be called autonomously per platform defaults, which is normal and appropriate for this type of skill.
Assessment
This skill is instruction-only and coherent with its purpose. Notes before installing: (1) it expects you (the agent) to call an external image model (Gemini) to render images — prompts and dialogue will be sent to that model/provider, so ensure you are comfortable with that data leaving your environment; (2) no credentials or system files are requested, so there is no obvious secret-exfiltration risk from the skill itself; (3) if you need offline or private rendering, configure your agent to use an on-prem or approved image model rather than a public Gemini endpoint; (4) avoid including private or sensitive personal data in the dialogue prompts since those will be transmitted to the image/model service.Like a lobster shell, security has layers — review code before you run it.
latestvk973tae7c4qh0fvzbmabbs9gj9829d1y
License
MIT-0
Free to use, modify, and redistribute. No attribution required.