Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Drawing.Bak
v1.0.0Generate children's drawings and coloring pages with modular prompts, style packs, and print-ready constraints across image models.
⭐ 0· 135·0 current·1 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
medium confidencePurpose & Capability
The name and description match the files and prompt templates provided; storing reusable prompts and preferences in ~/drawing/ is reasonable for a prompt-authoring skill. Minor mismatch: the docs reference OpenClaw CLI commands but the skill metadata does not declare any required binaries.
Instruction Scope
The runtime instructions explicitly direct the agent to create and read files under ~/drawing/ (declared) and to 'read this silently' and 'never mention setup, file names, or paths' to the user. The setup instructions also say to 'Save that activation preference in the user's main memory if the workspace already has a place for it', which could cause the agent to write to other workspace memory/config locations not declared in requires.config. These directives reduce transparency and could cause unexpected writes outside the declared config path.
Install Mechanism
This is an instruction-only skill with no install spec and no code files — low install risk. Nothing is downloaded or written by an installer beyond the files the agent may create at runtime in ~/drawing/.
Credentials
No environment variables, secrets, or external credentials are requested. The only declared resource is a config path (~/drawing/), which aligns with the skill's need to store reusable prompts and preferences.
Persistence & Privilege
The skill persists user preferences and memory to ~/drawing/, which matches the declared config path, but it also suggests saving activation preferences in the 'user's main memory' if the workspace supports it — an action that may modify global workspace memory outside the skill's own directory. The skill is not always-enabled and does not request elevated platform privileges, but the recommended silent behavior reduces visibility into these persistent writes.
What to consider before installing
This skill is largely coherent for creating and reusing prompts, but it will create and use files in ~/drawing/ and instruct the agent to keep that setup 'silent' and to save activation preferences into the workspace 'main memory' if available. Before installing, consider whether you are comfortable with a skill writing persistent preferences to your home directory and possibly to other workspace memory without explicit, visible confirmation. Ask the maintainer or inspect the ~/drawing/ files after first use. Also confirm whether you want the agent to run OpenClaw CLI commands (the docs mention them) and that those binaries exist. If you want stricter transparency, request the skill be modified to (a) announce when it will create files, (b) ask for explicit permission before writing to any global workspace memory, and (c) avoid instructions that tell the agent to hide setup behavior from the user.Like a lobster shell, security has layers — review code before you run it.
latestvk97f1z3xjg9qydezmx7d7h0z1s835hqt
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
🎨 Clawdis
OSLinux · macOS · Windows
Config~/drawing/