Skillv1.0.0

ClawScan security

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

BenignApr 28, 2026, 5:33 PM

Verdict: benign
Confidence: high
Model: gpt-5-mini
Summary: This is an instruction-only game-design auditing skill that is internally consistent with its stated purpose and does not request installs, credentials, or external network access.
Guidance: This skill appears safe and coherent: it is an instruction-only audit helper that reads its bundled taxonomy and produces design readings and recommendations. Before installing/using it, consider: (1) provenance — the owner and homepage are missing, so only use it if you trust the registry or reviewer; (2) data sharing — the skill will operate on whatever design text you provide, so avoid pasting confidential product specs or private user data into prompts; (3) review the included references/granular-taxonomy-notes.md to ensure the taxonomy matches your expectations. No credentials or system access are requested, so the technical risk is low.

Purpose & Capability: okThe skill's name, description, and included reference notes all align: it is a taxonomy-driven audit helper for game design. It requires no binaries, env vars, or external services to do its job. Minor provenance note: the package has no homepage and an unknown source/owner, which reduces provenance but does not contradict the stated purpose.
Instruction Scope: okSKILL.md instructs the agent to read the bundled references/granular-taxonomy-notes.md and produce an archetype-by-archetype audit and recommendations. All runtime instructions stay within the domain of design analysis and do not ask the agent to read unrelated system files, access environment variables, or transmit data to external endpoints.
Install Mechanism: okThere is no install spec and no code files — the skill is instruction-only, so nothing is written to disk or downloaded. This is the lowest-risk install model and is appropriate for a documentation/instruction skill.
Credentials: okThe skill requests no environment variables, no credentials, and no config paths. That is proportionate for a design-audit helper that operates purely on the included taxonomy and user-provided design descriptions.
Persistence & Privilege: okalways is false and the skill has default autonomous-invocation settings. Those defaults are normal; the skill does not request elevated persistence or system-wide changes and does not alter other skills' configs.