Back to skill
Skillv1.0.0
ClawScan security
Cross Team Plain Language · 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 writing helper for making cross-team messages clearer, with no code, credentials, installation steps, persistence, or external data access shown.
- Guidance
- This skill appears safe to install as a writing aid. As with any rewriting tool, review the final message before sending it, especially if it contains sensitive workplace context or could affect cross-team decisions.
Review Dimensions
- Purpose & Capability
- okThe artifacts consistently describe a plain-language rewriting skill that transforms messy or emotional workplace thoughts into clearer summaries and variants.
- Instruction Scope
- okInstructions are limited to editing, summarizing, asking minimal clarification questions, and offering tone variants; no tool use, autonomous actions, or authority escalation is requested.
- Install Mechanism
- okNo install specification, binaries, environment variables, credentials, or code files are present.
- Credentials
- okThe skill does not request access to files, network services, local system resources, accounts, or private stores.
- Persistence & Privilege
- okNo persistence, background behavior, credential use, memory storage, or privilege requirements are evidenced in the artifacts.