Back to skill
Skillv1.0.0
ClawScan security
Auditor · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignMay 1, 2026, 7:33 AM
- Verdict
- Benign
- Confidence
- high
- Model
- gpt-5.5
- Summary
- This is an instruction-only audit assistant whose stated behavior matches its purpose and does not request tools, credentials, installation, or persistent access.
- Guidance
- This skill appears safe to install based on the provided artifacts. Because audit tasks can involve confidential financial or compliance records, share only the information needed for the task and avoid unnecessary sensitive details.
Review Dimensions
- Purpose & Capability
- noteThe skill is coherently focused on audit planning, financial-record review, internal controls, and compliance; users should remember that audit work may involve sensitive business or financial information.
- Instruction Scope
- okInstructions are limited to defining scope, designing audit procedures, documenting findings, and recommending corrective actions; no hidden or unrelated behavior is evident.
- Install Mechanism
- okNo install spec, code files, binaries, environment variables, or package dependencies are present.
- Credentials
- okThe artifacts do not request local file access, network access, account access, credentials, or system permissions.
- Persistence & Privilege
- okNo persistence, background execution, privilege escalation, credential use, or autonomous mutation authority is described.