Skillv1.0.0

ClawScan security

Game Design Bartle Archetype Audit · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

BenignApr 21, 2026, 8:34 PM

Verdict: benign
Confidence: high
Model: gpt-5-mini
Summary: The skill is an instruction-only game-design audit that asks the agent to analyze designs through Bartle archetypes and it does not request unrelated permissions, installs, or credentials—its declared scope matches its actual requirements.
Guidance: This skill appears coherent and safe to install: it only contains instructions and reference notes for performing a Bartle-archetype audit. Before using it, avoid pasting unrelated secrets (API keys, private server URLs, etc.) into prompts or example game docs you provide to the agent. Also note that the agent may be allowed to invoke skills autonomously by default; if you don’t want autonomous runs, adjust skill invocation settings in your agent platform.

Purpose & Capability: okName/description, SKILL.md, and supporting reference files all describe a game-design audit. There are no unexpected env vars, binaries, or install steps; nothing requested is disproportionate to performing a design audit.
Instruction Scope: okRuntime instructions focus on evaluating game features against Achiever/Explorer/Socializer/Killer lenses and producing structured findings and recommendations. The instructions do not direct reading arbitrary system files, accessing credentials, or calling external endpoints.
Install Mechanism: okNo install spec and no code files beyond static reference MD files — nothing is downloaded or written to disk by the skill itself.
Credentials: okThe skill requires no environment variables, credentials, or config paths. The declared needs align with its stated purpose.
Persistence & Privilege: okalways is false and there are no indications the skill will modify other skills or system-wide settings. It does not request persistent presence or elevated privileges.