Back to skill
Skillv1.0.0
ClawScan security
Game Design Feature Prioritization · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 21, 2026, 12:06 PM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- This instruction-only skill is internally consistent with its stated purpose (prioritizing game features), requires no extra credentials or installs, and its instructions stay within the expected scope.
- Guidance
- This skill appears safe and coherent for prioritizing game design features. Before using it, avoid pasting sensitive credentials or proprietary files into prompts (the skill will use whatever you give it to form recommendations). If you want extra assurance, review the included references/family-conventions.md (it's present and harmless) and confirm you are comfortable with the agent producing prioritized outputs from any project data you provide.
Review Dimensions
- Purpose & Capability
- okThe name and description match the SKILL.md: the skill is a decision tool for prioritizing game features. It requests no binaries, env vars, or config paths—appropriate for an instruction-only prioritization helper.
- Instruction Scope
- okRuntime instructions only describe listing candidates, scoring them on impact/cost/fit/risk/timing, interpreting context, and recommending actions. The only referenced file is references/family-conventions.md, which is included and contains non-sensitive conventions. The instructions do not ask the agent to read unrelated system files, access credentials, or transmit data externally.
- Install Mechanism
- okNo install spec and no code files. Because this is instruction-only, nothing is written to disk or downloaded during install.
- Credentials
- okThe skill declares no required environment variables, credentials, or config paths. There is no disproportionate or unexplained secret access.
- Persistence & Privilege
- okalways is false and the skill is user-invocable; autonomous invocation is allowed by default on the platform but the skill does not request elevated or persistent privileges or modify other skills' configs.