Back to skill
Skillv1.0.0
ClawScan security
Universal Game Primitives · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignMay 1, 2026, 5:36 AM
- Verdict
- Benign
- Confidence
- high
- Model
- gpt-5.5
- Summary
- This is an instruction-only game architecture reference skill with no code execution, credentials, persistence, or sensitive data access shown.
- Guidance
- This appears safe to install as a documentation-style skill. It should help an agent structure game architecture explanations and examples, not run code or access your system.
Review Dimensions
- Purpose & Capability
- okThe artifacts consistently describe a DSL/reference guide for game and simulation architecture primitives, with examples and portability notes aligned to that purpose.
- Instruction Scope
- okInstructions focus on producing maps, diagrams, tables, pseudocode, and portability notes; there is no evidence of goal hijacking, hidden tool use, or unsafe autonomous actions.
- Install Mechanism
- okThe skill is instruction-only with no install specification, required binaries, packages, helper scripts, or executable code.
- Credentials
- okNo environment variables, credentials, config paths, OS-specific access, network calls, or local file access are requested.
- Persistence & Privilege
- okNo persistence, background activity, privilege escalation, account access, or stored memory behavior is evidenced in the artifacts.