Back to skill
Skillv2.0.0
ClawScan security
Game · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignMar 9, 2026, 5:29 AM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill is an instruction-only game design engine and its declared requirements and instructions are coherent and proportionate to that purpose.
- Guidance
- This skill is instruction-only and appears internally consistent for generating game designs. It's low-risk as provided because it requests no installs, files, or credentials. Before installing, review the full SKILL.md for any later sections that might ask the agent to fetch external assets or require API keys; if a future version adds code, downloads, or environment variables, re-evaluate for disproportionate access or network calls. Also avoid pasting any sensitive personal or credential information into prompts when using the skill.
Review Dimensions
- Purpose & Capability
- okName and description match the SKILL.md content: it generates playable game designs on text input. It requests no binaries, env vars, or installs that would be unnecessary for that function.
- Instruction Scope
- okThe SKILL.md contains design guidance and example outputs only; it does not instruct the agent to read files, access credentials, call external endpoints, or exfiltrate data. Truncated content continues the same design-focused guidance.
- Install Mechanism
- okNo install spec or code files are present. Being instruction-only means nothing will be written to disk or downloaded during install.
- Credentials
- okNo environment variables, credentials, or config paths are requested. There is no need for additional secrets to accomplish the stated purpose.
- Persistence & Privilege
- okalways is false and the skill is user-invocable. The skill does not request elevated or persistent platform privileges; autonomous invocation is allowed but is the platform default and not itself problematic here.