Back to skill
Skillv1.0.0
ClawScan security
openclaw context usage · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignMay 1, 2026, 8:21 AM
- Verdict
- Benign
- Confidence
- high
- Model
- gpt-5.5
- Summary
- This instruction-only skill is narrowly focused on reporting current context-window usage and shows no suspicious behavior.
- Guidance
- This skill appears safe to install if you want a quick summary of context-window usage. It does not request credentials, install code, or access files.
Review Dimensions
- Purpose & Capability
- okThe stated purpose is to show model name, token usage, cache information, and context utilization, and the instructions match that purpose.
- Instruction Scope
- okThe skill is invoked for user questions about context usage and instructs the agent to summarize a specific session-status field without changing settings or taking account actions.
- Install Mechanism
- okThere is no install spec and no code files; it is an instruction-only skill.
- Credentials
- okNo binaries, environment variables, credentials, config paths, file access, or network access are requested.
- Persistence & Privilege
- okThe artifacts show no persistence, background behavior, credential use, privilege escalation, or stored memory.