Back to skill
Skillv1.0.0
ClawScan security
Game Design Fairness Frustration Audit · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 26, 2026, 8:15 AM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill is an instruction-only game-design audit: its requirements, instructions, and included references are coherent with its stated purpose and do not request elevated privileges, external credentials, or risky installs.
- Guidance
- This skill appears safe and coherent: it only contains instructions and two reference documents used to shape output. Before using, avoid pasting secrets or private credentials into the audit prompt (the skill will analyze whatever you give it). Also be aware the agent is allowed to invoke skills autonomously by default — that's normal here but review agent-level permissions if you restrict autonomous actions.
Review Dimensions
- Purpose & Capability
- okThe name/description match the SKILL.md: it provides a structured audit for fairness and frustration in game design. No unrelated binaries, credentials, or config paths are requested.
- Instruction Scope
- okSKILL.md confines the agent to auditing the provided design/observations using included reference files. It does not instruct the agent to read system files, fetch external endpoints, or exfiltrate data. The references are bundled and purely stylistic/structural guidance.
- Install Mechanism
- okNo install spec or code files execute on the host — the skill is instruction-only, so nothing is written to disk or downloaded during install.
- Credentials
- okNo environment variables, credentials, or config paths are required. The skill does not request secrets or unrelated service tokens.
- Persistence & Privilege
- okalways is false and disable-model-invocation is false (the normal default). The skill does not request persistent system presence or modify other skills or agent configuration.