YouMind Blog Cover
Analysis
The skill mostly matches its blog-cover purpose, but it also grants unnecessary local Node execution permissions that are broader than needed.
Findings (5)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.
allowed-tools: - Bash(node -e *) - Bash(node scripts/*)
These permissions allow arbitrary inline Node execution and running local scripts, but the documented workflow only uses `youmind`, `npm install`, and an environment-variable check.
npm install -g @youmind-ai/cli
The skill asks the user to globally install an external npm CLI package. This is purpose-aligned, but the artifact does not pin a version.
If the agent platform supports subagents or background tasks, spawn a subagent for polling. Return control to the user immediately.
The skill can create a background polling task, but the provided polling rules bound it to 5-second polling with a 120-second timeout.
Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.
primaryEnv: YOUMIND_API_KEY requires: anyBins: ["youmind", "npm"] env: ["YOUMIND_API_KEY"]
The skill requires a YouMind API key to act on the user's YouMind account, which is expected for creating and saving generated images.
Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.
youmind call createChat '{"boardId":"<boardId>","message":"<optimized-prompt>","tools":{"imageGenerate":{"useTool":"required","aspectRatio":"16:9"}}}'The user's article title, topic, or URL is incorporated into a prompt sent to the external YouMind service for image generation.
