Back to skill
Skillv1.0.0
ClawScan security
Skill Development Guide / Skill 开发指南，tutorial, guide, skill, development, openclaw, qclaw, ai, mcp, how-to, 教程, 开发指南, skill-builder, clawhub · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignMay 1, 2026, 7:39 AM
- Verdict
- Benign
- Confidence
- high
- Model
- gpt-5.5
- Summary
- This is an instruction-only skill-development tutorial with sample templates and no code, credentials, persistence, or automatic actions.
- Guidance
- This skill appears safe as a tutorial. If you copy its optional script or external API examples into a real skill, review those new scripts, commands, and dependencies separately before publishing or installing.
Review Dimensions
- Purpose & Capability
- okThe artifacts consistently describe a tutorial for creating OpenClaw/ClawHub skills, and the included files are markdown examples and templates aligned with that purpose.
- Instruction Scope
- okThe instructions provide authoring guidance and example skill snippets; they do not direct the agent to override user intent, perform hidden actions, or treat external content as authoritative.
- Install Mechanism
- okThere is no install spec, no package dependency, and no runnable code in the supplied manifest.
- Credentials
- okNo binaries, environment variables, credentials, config paths, or capability tags are requested for this instruction-only guide.
- Persistence & Privilege
- okThe artifacts show no persistence mechanism, background behavior, credential use, account access, or privilege escalation.