Back to skill
Skillv0.1.1
ClawScan security
Creative Agent OS North Star · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignMay 1, 2026, 6:40 AM
- Verdict
- Benign
- Confidence
- high
- Model
- gpt-5.5
- Summary
- This is an instruction-only architecture review skill with no code, install steps, credentials, or authority to access or change user systems.
- Guidance
- This skill appears safe to install as a lightweight guidance document. It should influence architectural reviews only when relevant, and it does not add executable code or request access to your files, accounts, or environment.
Review Dimensions
- Purpose & Capability
- okThe artifacts consistently describe a product and architecture review aid for a lightweight creative agent OS, and the referenced north-star criteria align with that purpose.
- Instruction Scope
- okThe instructions focus on reviewing proposals against stated design principles and do not redirect user goals, require unsafe tool use, or make external content authoritative.
- Install Mechanism
- okThere is no install specification, no code files, no required binaries, and no package or script execution.
- Credentials
- okThe skill requests no environment variables, credentials, local configuration paths, network access, or system permissions.
- Persistence & Privilege
- okThe artifacts do not request persistent background behavior, privilege escalation, account access, or modification authority.