Back to skill
Skillv1.0.0
ClawScan security
周报速整助手 · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignMay 2, 2026, 11:29 PM
- Verdict
- Benign
- Confidence
- high
- Model
- gpt-5.5
- Summary
- This is an instruction-only weekly report formatting skill with no code, credentials, external services, or persistence.
- Guidance
- This skill appears safe for its purpose. As with any report-writing assistant, review the generated weekly report for accuracy before sharing it, especially if the input notes were vague.
Review Dimensions
- Purpose & Capability
- okThe stated purpose is to turn user-provided work notes into a structured weekly report, and the SKILL.md content stays within that writing/formatting task.
- Instruction Scope
- okInstructions define input handling, classification rules, formatting, and style guidance; they do not ask the agent to override user intent, use tools, access files, or perform actions outside report generation.
- Install Mechanism
- okNo install spec, binaries, environment variables, credentials, or code files are present.
- Credentials
- okThe skill does not request local system access, network access, account access, or other environmental permissions.
- Persistence & Privilege
- okThe artifacts show no persistence, background behavior, memory storage, privilege escalation, or autonomous mutation of user data.