Back to skill
Skillv1.0.0

ClawScan security

Game Design Emotional Canvas · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

Scanner verdict

BenignApr 21, 2026, 11:01 AM
Verdict
benign
Confidence
high
Model
gpt-5-mini
Summary
The skill is an instruction-only creative assistant for defining a game's emotional direction; its declared purpose, instructions, and resource requirements are internally consistent and proportional.
Guidance
This skill is coherent and low-risk: it only provides structured creative guidance and asks for no credentials or system access. Before installing, consider that (1) the agent may be allowed to call the skill autonomously under normal platform settings—review outputs before using them in production, and (2) never include secrets or private data in your prompts (the skill doesn't need them). If you want stricter control, keep autonomous invocation disabled or only call the skill manually.

Review Dimensions

Purpose & Capability
okName, description, and SKILL.md are aligned: the skill focuses on emotional identity, mood, and sensory direction for game content and does not request unrelated capabilities or credentials.
Instruction Scope
okRuntime instructions stay within the stated creative scope (generate target feeling, emotional texture, palette, anti-patterns, heuristics, evaluation, and a moodboard brief). The SKILL.md references only its included examples/prompts and does not direct the agent to read system files, environment variables, or external endpoints.
Install Mechanism
okNo install spec and no code files — instruction-only. Nothing is written to disk or fetched during install, so there is minimal install-time risk.
Credentials
okThe skill declares no required environment variables, credentials, or config paths. There are no requests for unrelated secrets or access.
Persistence & Privilege
okalways is false (normal). The skill may be invoked autonomously per platform defaults, which is expected for a user-invocable creative helper and does not by itself increase privilege beyond normal agent behavior.